© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    reasoning and problem solving

    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
    UCLEAR
    3.06
    तूल
    2.83
    <unused1658>
    2.81
     fishes
    2.80
    誦
    2.77
    诵
    2.73
    வனின்
    2.73
    ioribus
    2.71
    ujjati
    2.68
    iculis
    2.68
    POSITIVE LOGITS
    ir
    2.45
     jde
    2.42
    v
    2.33
     כך
    2.31
    or
    2.27
    c
    2.27
     daran
    2.26
    ্যাম
    2.22
    al
    2.22
    wohl
    2.21
    Activations Density 0.220%

    No Known Activations