© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    Estimados / Mean Squared

    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
     llevando
    2.70
     abbastanza
    2.60
    Przyp
    2.49
     assolutamente
    2.42
    𒁹
    2.38
     viendo
    2.35
     êtres
    2.34
    सायटी
    2.29
     alteraciones
    2.29
    شاف
    2.29
    POSITIVE LOGITS
    ’
    1.57
     aka
    1.56
     with
    1.52
     grabbed
    1.52
     (
    1.49
     and
    1.49
     from
    1.46
     cabbage
    1.45
     north
    1.42
     that
    1.42
    Activations Density 0.041%

    No Known Activations