© 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. 36864
    Prev
    Next
    INDEX
    Explanations

    linking tokens to next words

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

    deducted, subtracted, Snake game

    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
    ୬
    0.46
    给她
    0.44
    Allowance
    0.43
    撾
    0.42
    ٿ
    0.42
     neutrons
    0.41
    จะไม่
    0.41
     Mois
    0.41
     encycl
    0.41
    ተው
    0.41
    POSITIVE LOGITS
     옛
    0.50
    ложена
    0.46
    collisions
    0.46
    anı
    0.46
    collide
    0.46
     टकराव
    0.45
    plot
    0.44
    spanning
    0.44
    procedure
    0.44
    resu
    0.44
    Activations Density 0.000%

    No Known Activations