© 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. 165844
    Prev
    Next
    INDEX
    Explanations

    communicating or acting

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

    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
    Strafpunkte
    0.51
    屜
    0.51
    صیٰ
    0.50
    mataspid
    0.48
    िले
    0.47
    StoredKeys
    0.47
    鴦
    0.47
     Hispanics
    0.47
     предложения
    0.46
     শুধুমাত্র
    0.46
    POSITIVE LOGITS
    2
    0.68
    ?
    0.56
     jin
    0.53
    1
    0.50
    0
    0.50
     has
    0.49
     is
    0.48
    pl
    0.47
    flop
    0.46
    boro
    0.45
    Activations Density 0.000%

    No Known Activations