© 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. 90238
    Prev
    Next
    INDEX
    Explanations

    language diversity

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

    instructions and conditions

    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
    t
    0.67
    at
    0.63
    or
    0.54
    for
    0.54
     by
    0.51
    of
    0.50
    from
    0.50
    ore
    0.50
    when
    0.49
    is
    0.49
    POSITIVE LOGITS
    食べて
    0.50
    ╿
    0.49
    ╽
    0.48
     Tutak
    0.48
     mezcl
    0.47
    ScriptBuf
    0.45
     mieszkań
    0.45
     രാഷ്ട്ര
    0.45
     goomba
    0.45
    aarrggbb
    0.44
    Activations Density 0.001%

    No Known Activations