© 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. 122479
    Prev
    Next
    INDEX
    Explanations

    describing activities or conditions

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

    contrast or exception

    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
     cui
    0.52
    返回值
    0.50
     presenceData
    0.49
    总
    0.48
     érté
    0.48
    事實
    0.48
     wür
    0.47
    و
    0.47
    不錯
    0.46
     değeri
    0.46
    POSITIVE LOGITS
    thel
    0.47
    Employees
    0.45
    ーストラ
    0.45
    Comp
    0.43
    mates
    0.43
    tt
    0.43
    thyl
    0.43
     किये
    0.42
    ty
    0.42
    bers
    0.42
    Activations Density 0.000%

    No Known Activations