© 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. 236068
    Prev
    Next
    INDEX
    Explanations

    definition of terms and phrases

    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
    ጋገብ
    0.55
     studied
    0.49
     ਵ
    0.49
     杨
    0.49
     обычной
    0.49
     retrieving
    0.48
     revisited
    0.47
     purposeful
    0.46
     andDevice
    0.45
     commer
    0.45
    POSITIVE LOGITS
    اد
    0.52
    Pro
    0.52
    export
    0.50
    З
    0.50
    CREATE
    0.50
    POR
    0.48
    境界
    0.48
    pro
    0.47
    create
    0.47
    CAL
    0.47
    Activations Density 0.000%

    No Known Activations