© 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. 83665
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

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

    bear-resistant lockers and music

    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
    1
    0.49
    Cross
    0.46
    BRID
    0.46
    ele
    0.46
    跨
    0.44
    UTF
    0.43
    CROSS
    0.42
     suspensión
    0.42
     suspension
    0.42
    Brid
    0.42
    POSITIVE LOGITS
    ۴
    0.47
    ొ
    0.47
    ćem
    0.46
     ആദ്യം
    0.46
    病的
    0.45
    ۶
    0.45
    槤
    0.45
     Metern
    0.45
     astrophys
    0.44
     경우에는
    0.44
    Activations Density 0.000%

    No Known Activations