© 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. 243405
    Prev
    Next
    INDEX
    Explanations

    banking desks

    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
    ncol
    0.60
    vocab
    0.56
    km
    0.51
     }}>
    0.50
    atap
    0.49
    tcpHeader
    0.49
     emozioni
    0.49
     alcune
    0.48
     poems
    0.48
    ul
    0.47
    POSITIVE LOGITS
    argy
    0.49
    孭
    0.48
    Ќ
    0.47
    Α
    0.47
    Η
    0.45
    Џ
    0.45
    驸
    0.45
    ρά
    0.44
    Á
    0.43
    駙
    0.43
    Activations Density 0.000%

    No Known Activations