© 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. 60343
    Prev
    Next
    INDEX
    Explanations

    Philadelphia, sildenafil

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

    official app or ORG

    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
     Lockwood
    0.45
    र
    0.44
    噢
    0.43
    मग
    0.42
    Oh
    0.42
     Lobster
    0.41
    扃
    0.40
    גל
    0.40
    LastError
    0.40
    rą
    0.40
    POSITIVE LOGITS
     مشکلات
    0.39
     cultiv
    0.39
     음악
    0.39
     بغ
    0.37
     ذوالفقار
    0.37
    <td>
    0.37
     mencipt
    0.37
    }">${
    0.37
     życia
    0.36
    problems
    0.36
    Activations Density 0.000%

    No Known Activations