© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226386
    Prev
    Next
    INDEX
    Explanations

    business and research purposes

    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
    beg
    0.47
     TextField
    0.41
    —
    0.41
    bottomMargin
    0.40
    Tek
    0.40
    介
    0.40
     —
    0.40
    Te
    0.40
     Requires
    0.39
    …
    0.39
    POSITIVE LOGITS
    लॉक
    0.53
    ༥
    0.52
    ছনে
    0.51
    ahm
    0.50
     ऑब्जेक्ट
    0.49
     लॉक
    0.49
    தமிழ்
    0.48
    टीशन
    0.47
     वोट
    0.46
    ம்
    0.46
    Activations Density 0.001%

    No Known Activations