© 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. 120281
    Prev
    Next
    INDEX
    Explanations

    hazards, life, mind, oats, little

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

    little prediction, when is

    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
    html
    0.48
    Debug
    0.46
    EVENT
    0.45
    Č
    0.44
    onde
    0.44
    OLIS
    0.43
    هن
    0.41
    外
    0.41
     utilis
    0.41
    GG
    0.41
    POSITIVE LOGITS
    嘊
    0.52
    ક્રિયા
    0.49
     AdWords
    0.48
     сын
    0.47
     রাজপ
    0.47
     proactively
    0.46
     Palabra
    0.46
    シップ
    0.46
     стомато
    0.45
     американ
    0.45
    Activations Density 0.000%

    No Known Activations