© 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. 146015
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    African

    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
     آن‌ها
    0.48
    鎚
    0.46
    网
    0.45
    バー
    0.44
    ཎ
    0.44
    咄
    0.44
    锤
    0.44
    利用
    0.42
    مت
    0.42
    云
    0.42
    POSITIVE LOGITS
    ılarak
    0.49
    LongNumber
    0.48
    milliseconds
    0.47
     tributaries
    0.47
    '?
    0.46
    Subgraph
    0.45
     Edg
    0.45
     tributary
    0.45
    lilik
    0.45
    fiddle
    0.45
    Activations Density 0.001%

    No Known Activations