© 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. 6054
    Prev
    Next
    INDEX
    Explanations

    clean, sweep, shower

    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
    雎
    1.19
    ulat
    1.10
    </em>
    1.10
     AMERICA
    1.06
    iteten
    1.05
     CARL
    1.02
    igera
    1.01
     airliner
    1.01
     SURFACE
    1.01
     Reginald
    1.00
    POSITIVE LOGITS
    ##
    1.75
    ###
    1.75
    Dif
    1.73
    Checks
    1.70
    Token
    1.70
    `.
    1.67
    Recording
    1.64
    He
    1.61
    Score
    1.60
    `-
    1.60
    Activations Density 0.004%

    No Known Activations