© 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. 157308
    Prev
    Next
    INDEX
    Explanations

    CMP technical documentation

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

    detailed breakdown

    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
    sh
    0.55
    ran
    0.49
    da
    0.48
    <0x9B>
    0.46
     материа
    0.45
    rą
    0.45
    rk
    0.45
    daa
    0.45
    lor
    0.45
    sa
    0.44
    POSITIVE LOGITS
    $\--
    0.49
    大學
    0.49
     dlg
    0.48
     cursus
    0.47
    thinkable
    0.47
     dipende
    0.47
    頡
    0.47
    ６
    0.46
     universitaria
    0.45
     universitario
    0.45
    Activations Density 0.000%

    No Known Activations