© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    political and erotic story

    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
    -
    1.40
    '
    1.27
    (
    1.19
    .
    1.14
    ’
    1.06
    *
    1.02
    The
    0.98
    And
    0.93
    вЂ
    0.93
     (
    0.93
    POSITIVE LOGITS
    <unused71>
    1.72
    httpwwwpond
    1.72
    swadian
    1.71
    𒐊
    1.69
    𒌵
    1.67
    𒀫
    1.67
    𒐕
    1.67
     BusABC
    1.66
    𒅕
    1.66
    𒅋
    1.66
    Activations Density 0.145%

    No Known Activations