© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105679
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical or programming notation related to optimization problems, variables, constraints, and model definitions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on directive or action verbs in code or technical text (e.g. “create,” “set,” “compute,” “computes”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Redewendung
    -1.47
     Bewegungen
    -1.45
     кровать
    -1.44
    Their
    -1.40
    Dış
    -1.38
     preghi
    -1.31
     Auffassung
    -1.31
    These
    -1.31
    Out
    -1.30
     Handlungen
    -1.30
    POSITIVE LOGITS
     for
    1.52
     with
    1.41
    طلحات
    1.30
     चुनें
    1.26
     available
    1.22
     Wohnen
    1.22
     včetně
    1.21
    -
    1.21
    contato
    1.21
     any
    1.21
    Activations Density 0.067%

    No Known Activations