© 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. 19394
    Prev
    Next
    INDEX
    Explanations

    throughout the, for the

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

    traceable test cases or systems

    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
    риал
    0.54
    itabbo
    0.53
    ປະ
    0.51
    द्धाल
    0.51
    гова
    0.51
    ђено
    0.51
    唵
    0.51
     божомол
    0.50
    KU
    0.50
     腰
    0.50
    POSITIVE LOGITS
    an
    0.61
    in
    0.54
    s
    0.52
    te
    0.50
    chit
    0.48
    អំ
    0.47
     log
    0.46
    affirm
    0.46
    se
    0.46
    ac
    0.45
    Activations Density 0.000%

    No Known Activations