© 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. 217496
    Prev
    Next
    INDEX
    Explanations

    list and subsequent punctuation

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

    impacts and descriptions

    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
    ๔
    0.47
     espuma
    0.46
     in
    0.46
     zu
    0.45
     dans
    0.45
     tunnel
    0.44
    הר
    0.44
    ร
    0.44
     mechanical
    0.43
    にする
    0.43
    POSITIVE LOGITS
    alakip
    0.56
     கைப்ப
    0.55
     PDPN
    0.51
    adisu
    0.49
    jeron
    0.49
    amard
    0.48
    ushchev
    0.48
     CBP
    0.48
     getters
    0.48
     கதாபா
    0.47
    Activations Density 0.001%

    No Known Activations