© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11641
    Prev
    Next
    INDEX
    Explanations

    overflow or bursting

    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
    sectional
    1.35
    -
    1.30
     completely
    1.18
     tight
    1.17
    wall
    1.14
    mouth
    1.12
    legged
    1.11
     rough
    1.11
    down
    1.09
     breaking
    1.09
    POSITIVE LOGITS
     notificación
    2.02
    یسی
    1.96
    ඥ
    1.92
    íncipe
    1.92
     strListName
    1.90
    োহিত
    1.89
     внесен
    1.86
    цій
    1.84
    Declaration
    1.84
     jūn
    1.83
    Activations Density 0.035%

    No Known Activations