© 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. 95524
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or statements

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

    Schlossberg, California, Pasadena

    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
    रस
    0.51
    सरा
    0.46
    ные
    0.46
    رش
    0.45
    嵘
    0.45
    ার
    0.44
    мию
    0.43
     swirls
    0.43
    疯
    0.42
    طي
    0.42
    POSITIVE LOGITS
     γεν
    0.45
     passada
    0.44
     小型
    0.44
     Biele
    0.44
    ற்
    0.43
     بی
    0.43
     refundable
    0.43
     Kriegs
    0.42
    acidade
    0.42
    iação
    0.42
    Activations Density 0.000%

    No Known Activations