© 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. 22-GEMMASCOPE-RES-131K
    4. 98230
    Prev
    Next
    INDEX
    Explanations

    disposition notice

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

    The neuron detects high-level document section headings or metadata labels (e.g. Thesis, Award, Degree, term paper, Disposition, Decisions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.27
     The
    -1.20
     have
    -1.20
     are
    -1.14
     like
    -1.11
     first
    -1.09
     with
    -1.09
     http
    -1.09
     działa
    -1.05
     get
    -1.05
    POSITIVE LOGITS
    Université
    1.24
     compagnon
    1.23
    oléon
    1.23
     parfois
    1.21
    éez
    1.19
    킁
    1.17
    踌
    1.17
    sometimes
    1.16
    vantaged
    1.16
    Grazie
    1.15
    Activations Density 0.005%

    No Known Activations