© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6808
    Prev
    Next
    INDEX
    Explanations

    Covers

    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
    Negative Logits
     approx
    1.21
     !!!
    1.10
    !!!
    1.10
    !!!!
    1.08
     :-
    1.07
    !!!!!
    1.07
    :-
    1.06
     عباره
    1.05
    ;)
    1.03
     ONLY
    1.02
    POSITIVE LOGITS
     historian
    1.80
     commentators
    1.57
     pundits
    1.52
     novelist
    1.52
     sociologist
    1.49
     biographer
    1.49
     historians
    1.47
     admirers
    1.44
     commentator
    1.42
    Few
    1.42
    Activations Density 0.292%

    No Known Activations