© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    through thick and thin and accessed via

    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
    ać
    2.95
    oost
    2.86
    ingar
    2.61
    ﮄ
    2.59
    橥
    2.57
    eo
    2.52
    ので
    2.51
    िफिकेशन
    2.50
    chung
    2.46
     stanie
    2.42
    POSITIVE LOGITS
    ğın
    2.61
    অ
    2.21
    йн
    2.15
    |-|-
    2.15
    &-
    2.12
    >>;
    2.10
    wicket
    2.10
    IAL
    2.09
    ्यारह
    2.09
    櫚
    2.09
    Activations Density 0.000%

    No Known Activations