© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    best, ideal, recommended, key

    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
    阌
    2.76
     obice
    2.67
    ibilité
    2.66
     szczegól
    2.66
    糇
    2.63
    awać
    2.61
    लिसिस
    2.60
    পথে
    2.57
     antennis
    2.57
    捪
    2.56
    POSITIVE LOGITS
     out
    2.85
     away
    2.36
     up
    2.34
     down
    2.31
     Out
    2.31
    -
    2.11
     on
    2.08
     Class
    2.06
     forth
    2.00
     S
    1.95
    Activations Density 0.350%

    No Known Activations