© 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. 59466
    Prev
    Next
    INDEX
    Explanations

    Provider Open Houses

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

    achievable at home

    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
     as
    0.67
     by
    0.63
     for
    0.50
    ha
    0.48
    a
    0.48
    iano
    0.47
    asley
    0.47
    is
    0.45
    ipe
    0.45
     examines
    0.45
    POSITIVE LOGITS
    焼
    0.46
    團
    0.46
    CHEMICAL
    0.46
     ফ্যাস
    0.46
    ר
    0.45
     شود
    0.45
    רי
    0.44
    ריה
    0.44
    Š
    0.44
     issuance
    0.43
    Activations Density 0.000%

    No Known Activations