© 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. 196083
    Prev
    Next
    INDEX
    Explanations

    us

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

    specialized communication

    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
    ar
    0.57
    japan
    0.56
    rup
    0.55
    wu
    0.54
    rop
    0.54
    yim
    0.54
     रुक
    0.54
    ᆺ
    0.53
    in
    0.51
    sea
    0.51
    POSITIVE LOGITS
    ума
    0.48
     früheren
    0.46
     પ્રમા
    0.45
    记录
    0.45
    PlayerSelector
    0.45
    是
    0.44
    在这个
    0.44
    元素的
    0.43
    ColorF
    0.42
    平和
    0.42
    Activations Density 0.000%

    No Known Activations