© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3639
    Prev
    Next
    INDEX
    Explanations

    sleepless nights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    <bos>
    3.32
    ्‍य
    2.93
    توان
    2.80
    sman
    2.70
    es
    2.56
    opian
    2.52
    ॅमिली
    2.40
    ្ឋ
    2.38
    s
    2.37
    고
    2.33
    POSITIVE LOGITS
    SDLCheck
    3.28
    DebugSymbols
    2.98
    cartes
    2.80
    typeparam
    2.77
    FileAlignment
    2.67
     résoudre
    2.66
    ClInclude
    2.65
    Ὁ
    2.64
    ニーカー
    2.58
     possível
    2.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.