© 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. 116629
    Prev
    Next
    INDEX
    Explanations

    may increase, is required, suspended when

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

    intensity and qualification

    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
    周期
    0.47
    Chromosome
    0.46
    篾
    0.45
    机械
    0.44
    Clk
    0.43
    CBD
    0.43
    萆
    0.42
    Ⅲ
    0.42
    жд
    0.41
    TAM
    0.41
    POSITIVE LOGITS
     booths
    0.47
     archiv
    0.47
     marqu
    0.46
     इंटेलिज
    0.45
    thione
    0.45
     aumentare
    0.45
     entrev
    0.45
    ligere
    0.45
     हस्ता
    0.44
    cribes
    0.44
    Activations Density 0.000%

    No Known Activations