© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    find -type, GROUP BY

    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
    匾
    1.16
     End
    1.11
    Asc
    1.08
    End
    1.07
     प्रयोगशाला
    1.06
     hagas
    1.03
    Swatch
    1.03
    Ama
    1.01
    Ass
    0.98
     Gordo
    0.98
    POSITIVE LOGITS
     classified
    1.03
    utor
    0.94
    선을
    0.91
    classified
    0.90
    선
    0.88
    exponential
    0.85
    ående
    0.84
    adde
    0.82
     LTE
    0.82
     vacations
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.