© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    volcanic activity and features

    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
    ம்தா
    2.32
     Thiết
    2.02
    дцать
    2.00
    ANCIS
    1.95
    ಥವಾ
    1.94
    <unused381>
    1.90
    Ự
    1.89
     특집
    1.88
     공유
    1.88
     애
    1.85
    POSITIVE LOGITS
    om
    1.66
    p
    1.60
    ia
    1.49
    at
    1.46
    u
    1.45
    in
    1.44
    h
    1.44
    inä
    1.43
    g
    1.42
    г
    1.38
    Activations Density 0.000%

    No Known Activations