© 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. 8261
    Prev
    Next
    INDEX
    Explanations

    look for

    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
     liquefied
    0.85
    jectories
    0.83
     vigueur
    0.82
     reckoning
    0.80
    狩
    0.79
    火力
    0.79
    ικ
    0.79
    詔
    0.79
    فاوت
    0.78
    eger
    0.78
    POSITIVE LOGITS
     unrelated
    1.57
     trivial
    1.54
     obvious
    1.50
     simple
    1.48
     mundane
    1.44
     banal
    1.37
    simple
    1.37
     unimportant
    1.29
     cliche
    1.28
     бана
    1.27
    Activations Density 0.326%

    No Known Activations