© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1680
    Prev
    Next
    INDEX
    Explanations

    inseparable since, active wear

    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
    rparam
    0.93
    𐰆
    0.92
     minifyEnabled
    0.91
    <unused1201>
    0.91
    openide
    0.91
    𒊭
    0.91
    <unused298>
    0.91
     elytris
    0.90
     vattum
    0.90
    Trashed
    0.90
    POSITIVE LOGITS
    E
    0.75
     and
    0.73
     E
    0.70
    .
    0.65
     on
    0.64
    '
    0.63
     of
    0.63
    -
    0.62
     in
    0.61
    Y
    0.60
    Activations Density 0.000%

    No Known Activations