© 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. 53909
    Prev
    Next
    INDEX
    Explanations

    the current state or outcome

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

    money, numbers, and history

    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
     fila
    0.60
     Komitet
    0.50
     courbe
    0.50
     pouls
    0.49
     canzone
    0.49
     protesta
    0.48
    JSPA
    0.48
    𝖐
    0.47
     farce
    0.47
     podpis
    0.47
    POSITIVE LOGITS
     المعروف
    0.46
    嚿
    0.44
     knew
    0.42
     $
    0.42
     SUCCESS
    0.41
     Replacement
    0.41
     replacement
    0.41
     configured
    0.41
    ู้
    0.40
    QueryResult
    0.40
    Activations Density 0.000%

    No Known Activations