© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9718
    Prev
    Next
    INDEX
    Explanations

    date formats

    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
    %-
    1.16
    %)
    1.11
     \%$
    1.10
    %
    1.08
     \%)$
    1.07
    \%
    0.99
    %+
    0.97
    ％
    0.96
     granit
    0.96
    PERCENT
    0.92
    POSITIVE LOGITS
     लग
    0.93
     लगता
    0.80
    ెల
    0.79
    今の
    0.78
    мести
    0.78
     credo
    0.76
    вори
    0.76
    числи
    0.76
    ключа
    0.76
    ä
    0.76
    Activations Density 0.083%

    No Known Activations