© 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. 105319
    Prev
    Next
    INDEX
    Explanations

    translation and replacement procedures

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

    LinkedIn, register, organic milk, downs

    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
    </span>
    0.46
    imwrite
    0.45
    equation
    0.45
    <unused60>
    0.42
    の発
    0.41
    eqnarray
    0.41
    import
    0.41
    support
    0.41
    ]}{
    0.41
    mathop
    0.40
    POSITIVE LOGITS
    死去
    0.49
     begun
    0.48
    人民币
    0.48
    失去了
    0.45
    开始了
    0.44
    死了
    0.42
    ૂર્
    0.42
     clums
    0.42
     personenbez
    0.42
    的人生
    0.42
    Activations Density 0.002%

    No Known Activations