© 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. 10009
    Prev
    Next
    INDEX
    Explanations

    drag photos into

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

    counting and examples

    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
    Hval
    0.43
     concomit
    0.40
     sapp
    0.40
    वाधिकार
    0.40
    acoes
    0.39
    ‴
    0.39
     grotes
    0.39
    esine
    0.39
     associé
    0.39
     flexion
    0.38
    POSITIVE LOGITS
    open
    0.39
     শুরু
    0.38
    ade
    0.37
    闖
    0.36
    开放
    0.35
     開始
    0.35
    observation
    0.35
    ныгы
    0.35
    pur
    0.34
    開始
    0.34
    Activations Density 0.000%

    No Known Activations