© 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. 25127
    Prev
    Next
    INDEX
    Explanations

    numbered lists

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

    rule, selling, Chartered

    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
    Device
    0.39
    Whitelist
    0.38
    ReturnValue
    0.38
    讵
    0.38
    carboxylate
    0.37
    SystemCall
    0.37
    ።
    0.37
     กรณี
    0.37
    StateMachine
    0.36
    anjian
    0.36
    POSITIVE LOGITS
     andre
    0.40
     Á
    0.37
     clums
    0.37
     poli
    0.37
     clonal
    0.37
     ou
    0.37
     ateliers
    0.36
     latin
    0.36
     Eds
    0.36
     ogn
    0.36
    Activations Density 0.000%

    No Known Activations