© 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. 14536
    Prev
    Next
    INDEX
    Explanations

    getting finding challenge

    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
    out
    1.06
    orm
    1.04
    red
    0.95
    int
    0.91
    un
    0.89
    Р
    0.87
    ur
    0.86
    ist
    0.86
    ook
    0.84
    R
    0.84
    POSITIVE LOGITS
    <unused1361>
    2.07
    <unused1182>
    2.05
    <unused466>
    2.02
    <unused2102>
    2.00
    <unused1208>
    2.00
    <unused407>
    2.00
    <unused1201>
    2.00
    <unused895>
    1.97
    <unused1996>
    1.96
    <unused488>
    1.96
    Activations Density 0.106%

    No Known Activations