© 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. 117010
    Prev
    Next
    INDEX
    Explanations

    specific categories and their relations

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

    loguru, forces, concurrent, resizing

    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
    苏
    0.46
     suited
    0.45
    Su
    0.44
    ্রম
    0.44
     lineWidth
    0.43
     acronym
    0.42
     milky
    0.42
     "$"
    0.42
    话说
    0.42
    Stein
    0.41
    POSITIVE LOGITS
     हाइड्रोजन
    0.54
    kę
    0.52
    ni
    0.51
    oscope
    0.50
    na
    0.50
    orul
    0.50
    ga
    0.49
    kken
    0.49
     battalions
    0.49
     جغ
    0.49
    Activations Density 0.000%

    No Known Activations