© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5759
    Prev
    Next
    INDEX
    Explanations

    plotting with colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ↵↵↵↵↵↵
    1.11
     formation
    1.04
     Lak
    1.04
     Phenomen
    1.01
    <h6>
    1.00
     strument
    0.99
     Governmental
    0.96
    ↵↵↵↵↵
    0.96
     Workout
    0.96
    <start_of_image>
    0.95
    POSITIVE LOGITS
    jén
    1.76
    roff
    1.72
     abon
    1.71
     одном
    1.68
     sửa
    1.67
    entery
    1.67
    筞
    1.66
     tấn
    1.66
    error
    1.64
    ρίς
    1.64
    Activations Density 0.011%

    No Known Activations