© 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. 58673
    Prev
    Next
    INDEX
    Explanations

    compose or Cole on typing succeed confirm on host schedule

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

    operating on mathematical and scientific terms

    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
     depreciation
    0.47
    အတွ
    0.42
     manager
    0.41
     zaken
    0.41
     bowel
    0.40
     managers
    0.40
    ებულია
    0.39
    е
    0.39
     improvements
    0.39
    と思いますが
    0.39
    POSITIVE LOGITS
    Mord
    0.49
     než
    0.47
    PerTrial
    0.47
    Operand
    0.46
    FromThe
    0.43
     Mena
    0.42
    ʽ
    0.42
    真正
    0.42
     المقدس
    0.42
    ണ്ട്
    0.42
    Activations Density 0.000%

    No Known Activations