© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    phone numbers and identifiers

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

    crisis support services

    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
    ంగా
    0.68
    ाम
    0.67
    าย
    0.65
    ката
    0.64
     سرحد
    0.64
    awning
    0.63
    و
    0.63
    apä
    0.62
    ала
    0.61
    ،
    0.61
    POSITIVE LOGITS
    TE
    0.71
    do
    0.68
    rt
    0.68
    TS
    0.68
    rd
    0.66
    rrr
    0.66
    IL
    0.66
     lire
    0.66
    rr
    0.65
    ji
    0.64
    Activations Density 0.059%

    No Known Activations