© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    cluster `get` cert

    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
    ಿ
    2.82
    ীশ
    2.57
    ي
    2.53
    ील
    2.52
    м
    2.45
    es
    2.45
    ו
    2.42
    fread
    2.29
    y
    2.22
    այն
    2.19
    POSITIVE LOGITS
     teg
    2.12
    ރ
    2.06
    érations
    2.00
    tre
    1.93
    𝐨
    1.92
    ".$
    1.92
    ރު
    1.90
    laget
    1.89
    σεις
    1.88
    鋈
    1.87
    Activations Density 0.128%

    No Known Activations