© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7762
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_22_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
     Oni
    1.19
     (-
    1.16
    ccgi
    1.14
     (−
    1.12
     (),
    1.12
     ()
    1.11
     ー
    1.09
    iré
    1.07
    comics
    1.06
     (+
    1.06
    POSITIVE LOGITS
    ?).
    0.99
    ไหน
    0.99
     or
    0.94
    ?”.
    0.91
    ?".
    0.89
     what
    0.86
    ?}
    0.86
    }.
    0.84
    ?]
    0.83
    ?")
    0.82
    Activations Density 0.006%

    No Known Activations