© 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. 20508
    Prev
    Next
    INDEX
    Explanations

    local or maximum extent

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

    control the training process

    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
    ק
    0.45
    getHeader
    0.41
    neis
    0.40
    マス
    0.39
    тей
    0.39
    ực
    0.38
    кон
    0.38
    伸
    0.38
    هر
    0.37
    ᄐ
    0.37
    POSITIVE LOGITS
     lokale
    0.51
     ឬ
    0.51
     lokal
    0.50
     maximale
    0.49
    എ
    0.48
    local
    0.48
     xhrObj
    0.48
     somebody
    0.47
     axb
    0.47
     واللي
    0.46
    Activations Density 0.000%

    No Known Activations