© 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. 72542
    Prev
    Next
    INDEX
    Explanations

    woodinville wa

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

    indeed

    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
     హె
    0.49
    ज्ञानिक
    0.48
    ＮＡ
    0.46
    Ｈ
    0.45
    ｭ
    0.45
     HTTPException
    0.44
    𝚎
    0.44
     fenô
    0.44
    <unused13>
    0.44
    үл
    0.44
    POSITIVE LOGITS
    -
    0.49
     খ
    0.49
    भर
    0.49
    সে
    0.48
     .
    0.48
     cầm
    0.48
     subwoofer
    0.48
     Colchester
    0.46
     selection
    0.45
    /
    0.44
    Activations Density 0.000%

    No Known Activations