© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    request exception

    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
    При
    2.77
    бли
    2.74
    У
    2.73
    Descripcion
    2.67
    гиз
    2.67
    约翰
    2.65
     padres
    2.58
     ОС
    2.56
     atrás
    2.53
    Фор
    2.53
    POSITIVE LOGITS
    ed
    2.80
    unak
    2.57
    nights
    2.50
    rainian
    2.47
    ा
    2.37
    oliko
    2.36
    dun
    2.36
    ulet
    2.34
    rece
    2.32
    inescent
    2.31
    Activations Density 0.017%

    No Known Activations