© 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. 10953
    Prev
    Next
    INDEX
    Explanations

    documentation tutorials queries

    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
    दायक
    2.41
    no
    2.31
    igung
    2.26
    ادي
    2.23
    na
    2.17
    ୱ
    2.17
    īd
    2.16
    sa
    2.15
    iejs
    2.15
    eli
    2.14
    POSITIVE LOGITS
    ോധ
    3.22
    ી
    2.91
    halla
    2.91
    ಸ್ತಕ
    2.87
    猬
    2.86
    DbType
    2.85
    рити
    2.77
    ی
    2.76
    evice
    2.74
    coprote
    2.73
    Activations Density 0.005%

    No Known Activations