© 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. 64423
    Prev
    Next
    INDEX
    Explanations

    art and explanations

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

    special/stimulating content

    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
     in
    0.56
    va
    0.54
    wania
    0.46
    ,
    0.45
     and
    0.44
    ванный
    0.43
     Sharp
    0.42
    owa
    0.42
    .*;
    0.42
    val
    0.42
    POSITIVE LOGITS
     ឬ
    0.52
    ЕС
    0.50
    ㄶ
    0.49
     próximas
    0.49
    ل
    0.48
    同行
    0.48
    operateur
    0.47
     mulut
    0.47
    სახ
    0.47
    स
    0.46
    Activations Density 0.000%

    No Known Activations