© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193422
    Prev
    Next
    INDEX
    Explanations

    legal and procedural actions

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

    explaining why resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infirm
    0.48
     Daytime
    0.45
     Chosen
    0.45
     dal
    0.45
     Noon
    0.45
    中午
    0.42
     מ
    0.41
     달
    0.41
     Noct
    0.41
    endim
    0.41
    POSITIVE LOGITS
     কারনে
    0.44
    ৌজের
    0.44
    નને
    0.43
    장의
    0.43
     slowdown
    0.42
     sanitize
    0.42
     შეიძლება
    0.42
    اتر
    0.41
    消毒
    0.41
     slowing
    0.41
    Activations Density 0.000%

    No Known Activations