© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 88075
    Prev
    Next
    INDEX
    Explanations

    education, pollution, seasonal, hunting, mystery, protests

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

    obedience, trafficking, newspaper excerpt

    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
    ת
    0.53
    Updated
    0.49
    विचार
    0.47
    Sono
    0.47
    On
    0.46
    Passport
    0.46
    Ciao
    0.46
    Telefon
    0.46
    ป
    0.46
    Teste
    0.45
    POSITIVE LOGITS
     entitles
    0.49
     unskilled
    0.48
     litigants
    0.48
     ridd
    0.47
     tries
    0.45
     rctx
    0.44
     Hep
    0.43
     entails
    0.43
     equates
    0.43
     emits
    0.43
    Activations Density 0.003%

    No Known Activations