© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 8889
    Prev
    Next
    INDEX
    Explanations

    official designations and reports

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

    fortran and mojo code

    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_40_width_16k_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
    ,$
    0.42
    ूं
    0.39
    ool
    0.39
    ALCHEMY
    0.39
    inky
    0.38
     marvellous
    0.38
    ging
    0.37
     irresist
    0.37
     revolved
    0.37
     dagen
    0.37
    POSITIVE LOGITS
     offenses
    0.52
    认定
    0.49
    関連項目
    0.47
    推定
    0.46
     designations
    0.45
    魟
    0.44
     اہمیت
    0.44
    हर
    0.44
     offense
    0.42
    対象
    0.42
    Activations Density 0.001%

    No Known Activations