© 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. 163709
    Prev
    Next
    INDEX
    Explanations

    documentation, methodology, exploration, username

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

    bank conversion

    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
    en
    0.44
    getElementById
    0.43
    ibilidad
    0.42
     roomy
    0.42
    ₹
    0.42
    phone
    0.42
     உன்
    0.41
     usando
    0.41
    bollywood
    0.40
     aumenta
    0.39
    POSITIVE LOGITS
    ULU
    0.51
    組み立て
    0.50
    DAMAGE
    0.48
     الموسم
    0.47
     Moc
    0.46
     prépar
    0.46
    ോ
    0.46
    THERE
    0.45
    ↵
    0.45
    هدف
    0.45
    Activations Density 0.000%

    No Known Activations