© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58525
    Prev
    Next
    INDEX
    Explanations

    foreign language commerce

    np_acts-logits-general · gemini-2.5-flash-lite

    Morse code sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ↵↵
    0.46
     clipped
    0.45
     узна
    0.45
     tòa
    0.43
     excavated
    0.43
    </h2>
    0.42
     }}$
    0.42
    най
    0.41
     exh
    0.41
     extracted
    0.41
    POSITIVE LOGITS
    代言
    0.54
     verkauft
    0.50
    رهای
    0.47
    ری
    0.45
    ricorn
    0.45
     متنوع
    0.45
    র্শ
    0.44
     türk
    0.44
     nächsten
    0.43
     শ
    0.43
    Activations Density 0.000%

    No Known Activations