© 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. 96473
    Prev
    Next
    INDEX
    Explanations

    Common phrases and sequences

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

    chess openings or code

    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
    /
    0.64
    !
    0.61
    ↵↵
    0.57
    Park
    0.53
    Pair
    0.52
    +
    0.52
    Order
    0.50
    Mult
    0.50
    ovich
    0.50
    ack
    0.50
    POSITIVE LOGITS
     partito
    0.53
    ൻസ്
    0.51
    铧
    0.50
    데이트
    0.49
    俔
    0.49
    庣
    0.49
    ැ
    0.48
     lehetős
    0.48
    зона
    0.48
    眝
    0.48
    Activations Density 0.000%

    No Known Activations