© 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. 65436
    Prev
    Next
    INDEX
    Explanations

    You know, is this over use patients captures as about

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

    upcoming advanced

    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
     rows
    0.54
     whereupon
    0.54
     Rows
    0.54
    ópolis
    0.50
     brackets
    0.50
    //*
    0.49
     Denison
    0.48
     envelopes
    0.48
     interfaces
    0.47
     volts
    0.47
    POSITIVE LOGITS
    на
    0.48
    다
    0.46
     kell
    0.46
    虾
    0.46
    暇
    0.44
    е
    0.44
    大型
    0.43
    anja
    0.42
     injuring
    0.42
    年度
    0.42
    Activations Density 0.000%

    No Known Activations