© 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. 142192
    Prev
    Next
    INDEX
    Explanations

    requirements after his data

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

    enumeration with colons or periods

    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
    a
    0.51
    <h2>
    0.46
    iazioni
    0.45
    partners
    0.44
     acronym
    0.43
    嫻
    0.43
    ા
    0.43
    letters
    0.42
     ELSE
    0.42
     finns
    0.42
    POSITIVE LOGITS
     جشنواره
    0.51
     Ghosts
    0.49
     これは
    0.48
    henderit
    0.47
     চলচ্চিত্রের
    0.46
    ${\
    0.46
     চতুর্থ
    0.46
     alimentación
    0.46
     アウトドア
    0.45
     Ettha
    0.44
    Activations Density 0.000%

    No Known Activations