© 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. 204078
    Prev
    Next
    INDEX
    Explanations

    Principal Meridian, watch, have been, final four, true, year, line

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

    Lifecycle Management

    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
    ǿ
    0.46
     responsabilité
    0.44
     salarié
    0.44
     miRNA
    0.43
     rival
    0.43
     clash
    0.43
     Bonne
    0.43
     Cauchy
    0.42
     Caro
    0.42
     Prest
    0.42
    POSITIVE LOGITS
    }|
    0.48
    FlowNode
    0.47
    AD
    0.46
    ;|
    0.45
    avanje
    0.45
    핀
    0.44
    ける
    0.44
    хара
    0.43
    сля
    0.42
    >{
    0.42
    Activations Density 0.000%

    No Known Activations