© 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. 121722
    Prev
    Next
    INDEX
    Explanations

    repair or replacement

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

    threat, highest, summit

    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
    ㄽ
    0.53
     prépuce
    0.52
    sendKeyDown
    0.51
     médicale
    0.51
     "????.??.??"]
    0.51
     sparsim
    0.51
    づくり
    0.50
     পালিয়ে
    0.49
     গল্প
    0.49
    流
    0.49
    POSITIVE LOGITS
     Marc
    0.49
     Silverman
    0.49
     N
    0.48
     Palmer
    0.45
     Wellington
    0.45
     Pric
    0.44
     Tom
    0.43
     Edmunds
    0.42
     Chilton
    0.42
     Theodor
    0.42
    Activations Density 0.000%

    No Known Activations