© 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. 155758
    Prev
    Next
    INDEX
    Explanations

    took place, unique toys, other guests, fighting against

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

    HTML snippets and code explanations

    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
    جیت
    0.46
     carico
    0.46
    ┝
    0.45
     Admit
    0.44
    VERSION
    0.43
     alternatively
    0.43
     atomically
    0.43
    Ξ
    0.42
     labeled
    0.41
    相続
    0.41
    POSITIVE LOGITS
     ១
    0.49
     وتش
    0.46
     وتن
    0.46
    }'
    0.45
    maal
    0.45
    惘
    0.45
     Einführung
    0.44
     kort
    0.44
     nd
    0.43
    jan
    0.43
    Activations Density 0.000%

    No Known Activations