© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    beach, house, offers

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

    svg and image links

    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
    潾
    0.50
    <unused44>
    0.48
     outpatient
    0.46
     televisi
    0.45
    इंड
    0.45
    eraient
    0.45
    スタンダ
    0.45
     matematica
    0.43
    ousands
    0.43
    outez
    0.43
    POSITIVE LOGITS
     C
    0.49
    C
    0.47
    Win
    0.43
     kick
    0.42
    ,
    0.42
     Win
    0.40
    台
    0.40
     Post
    0.39
    机
    0.39
    .
    0.39
    Activations Density 0.014%

    No Known Activations