© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14475
    Prev
    Next
    INDEX
    Explanations

    gradually introduce, with a

    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_13_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
     drastic
    1.18
    <unused1227>
    1.17
    <unused1231>
    1.16
    <unused298>
    1.16
    <unused1026>
    1.14
    <unused589>
    1.14
    <unused248>
    1.13
    <unused2090>
    1.13
     fantastical
    1.13
     blatant
    1.13
    POSITIVE LOGITS
    -
    0.94
    _
    0.77
     которой
    0.76
    và
    0.75
    .
    0.74
     và
    0.73
    +
    0.73
     และ
    0.72
    ’
    0.71
    q
    0.71
    Activations Density 0.208%

    No Known Activations