© 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. 190320
    Prev
    Next
    INDEX
    Explanations

    businesses operating simply

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

    crucial process, document, or part

    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
    classroom
    0.47
    𒉿
    0.47
     önemli
    0.46
     Ormond
    0.46
    тері
    0.46
    ক্ট
    0.46
     सुर्ख
    0.45
     दुर्लभ
    0.45
     biomark
    0.44
     vitesses
    0.44
    POSITIVE LOGITS
    羲
    0.47
    하다고
    0.45
    has
    0.44
    יין
    0.44
    hiva
    0.44
    AGEN
    0.42
    常见
    0.40
    ｈ
    0.40
    시키는
    0.40
     golpe
    0.40
    Activations Density 0.000%

    No Known Activations