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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41018
    Prev
    Next
    INDEX
    Explanations

    user, notification, header, criminal

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

    The neuron fires on identifiers that appear after a “.” in code (i.e. object or field names accessed via dot notation).

    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
     is
    -1.53
     how
    -1.30
     которые
    -1.21
     graden
    -1.19
     другие
    -1.13
     jego
    -1.12
     autonomie
    -1.12
    ceased
    -1.11
    necessary
    -1.09
     dwóch
    -1.09
    POSITIVE LOGITS
     perils
    1.34
    рення
    1.30
    了几
    1.27
     superbly
    1.27
    rophoto
    1.24
     longstanding
    1.20
     predominant
    1.16
    entista
    1.16
     it
    1.16
     modest
    1.16
    Activations Density 0.153%

    No Known Activations