© 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. 3040
    Prev
    Next
    INDEX
    Explanations

    smoothie, imshow

    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
     urged
    1.88
    planade
    1.78
     acclaimed
    1.73
     delegation
    1.70
     highlighted
    1.69
    ’
    1.67
     spearheaded
    1.66
     reiterated
    1.64
     underscored
    1.63
    \-
    1.57
    POSITIVE LOGITS
     zásobníku
    1.30
    Flipper
    1.29
     Celui
    1.28
    පු
    1.28
    λώ
    1.23
    INGS
    1.22
    ذا
    1.20
     Unters
    1.20
     plaisir
    1.19
     rozpozn
    1.17
    Activations Density 0.094%

    No Known Activations