© 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. 55125
    Prev
    Next
    INDEX
    Explanations

    code comments and file operations

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

    description perfectlyeven accidentaleven attemptingsearch )statement directly

    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
    转变
    0.47
     ប
    0.45
     persamaan
    0.43
    摄像
    0.43
     عين
    0.42
     tuj
    0.42
    卷
    0.41
     ular
    0.41
     média
    0.41
    <0x8D>
    0.41
    POSITIVE LOGITS
    Jadi
    0.54
    c
    0.46
    umball
    0.46
    Pada
    0.44
    oliko
    0.44
     thrown
    0.43
    jadi
    0.43
    </code>
    0.42
    baka
    0.42
     needing
    0.41
    Activations Density 0.000%

    No Known Activations