© 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. 113616
    Prev
    Next
    INDEX
    Explanations

    confirmation, support, flexible, universal

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

    Indian civilization, Signal and Systems, robot perception, compounds, Tuesday, Chinese culture

    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
    nunique
    0.53
    on
    0.50
    엘
    0.49
    ন
    0.48
    كو
    0.47
    из
    0.47
    و
    0.47
    از
    0.46
     нормально
    0.46
    бо
    0.45
    POSITIVE LOGITS
     লিখিত
    0.49
     Witten
    0.46
     Vedic
    0.46
     Curran
    0.45
     professe
    0.44
     Gérard
    0.44
     special
    0.44
     പ്രധാന
    0.44
     Guten
    0.44
     vaccine
    0.42
    Activations Density 0.000%

    No Known Activations