© 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. 38141
    Prev
    Next
    INDEX
    Explanations

    authorized attempt

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

    come and gone

    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
    ADMIN
    0.47
     albo
    0.46
    lycerin
    0.46
    STD
    0.43
     evaporated
    0.42
    ステル
    0.42
    SUMMARY
    0.42
    ("#{
    0.42
    COMMON
    0.41
    ícito
    0.41
    POSITIVE LOGITS
     न्यून
    0.48
    璋
    0.47
     науки
    0.46
     VGA
    0.46
     Watford
    0.45
    graphics
    0.44
     क्वांट
    0.44
    ahm
    0.43
     நிறுவனம்
    0.43
    yama
    0.43
    Activations Density 0.000%

    No Known Activations