© 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. 19285
    Prev
    Next
    INDEX
    Explanations

    types and categories

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

    ```. elab >```

    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
    द
    0.52
    তাদের
    0.48
     welcoming
    0.47
    وی
    0.47
    颢
    0.44
    രിച്ചത്
    0.43
    ویی
    0.41
    М
    0.41
     noteworthy
    0.41
    ুদের
    0.40
    POSITIVE LOGITS
     manzanas
    0.49
    writelines
    0.49
    两种
    0.48
    是一種
    0.47
    brahim
    0.46
    兩種
    0.46
    ಿಕ್
    0.46
    मर्रा
    0.45
    ácter
    0.45
    ធម្ម
    0.45
    Activations Density 0.000%

    No Known Activations