© 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. 12317
    Prev
    Next
    INDEX
    Explanations

    A/B testing

    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
    <bos>
    2.72
    nm
    2.40
    нский
    2.35
    umbing
    2.30
     gib
    2.27
    橥
    2.26
    anship
    2.23
    度が
    2.23
    度
    2.17
    opically
    2.12
    POSITIVE LOGITS
    பிள்
    2.59
    assadors
    2.48
    getTarget
    2.37
    assador
    2.31
    ставить
    2.24
    Yes
    2.21
     गरीब
    2.20
    гент
    2.14
    ەش
    2.13
    apsingToolbar
    2.13
    Activations Density 0.010%

    No Known Activations