© 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. 133494
    Prev
    Next
    INDEX
    Explanations

    calculator and weight

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

    lottery numbers birthdays

    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
    t
    0.50
    s
    0.49
    r
    0.44
    orical
    0.44
    র্
    0.42
    es
    0.42
    son
    0.42
    től
    0.42
    rini
    0.41
    ega
    0.41
    POSITIVE LOGITS
     COVID
    0.49
     uso
    0.45
    COVID
    0.44
     IU
    0.44
     použití
    0.44
     يُ
    0.43
     እነዚህ
    0.43
     कोविड
    0.43
     الطبي
    0.43
     העולם
    0.42
    Activations Density 0.001%

    No Known Activations