© 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. 133317
    Prev
    Next
    INDEX
    Explanations

    various language characters

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

    headings and lists

    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
     Conley
    0.46
    }}:
    0.44
    DEBUGFS
    0.43
    🎬
    0.42
    NEL
    0.42
     multitudes
    0.41
    Purg
    0.41
    澡
    0.40
    Alive
    0.40
    lmfit
    0.40
    POSITIVE LOGITS
    ända
    0.54
     타이
    0.47
     यांनी
    0.47
    ოდ
    0.46
    인다
    0.46
     북
    0.45
    året
    0.44
     cobre
    0.44
    ikk
    0.44
     ფ
    0.44
    Activations Density 0.000%

    No Known Activations