© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144487
    Prev
    Next
    INDEX
    Explanations

    shapes, mass, relations, pink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಬೇ
    0.45
     intermolecular
    0.44
     আত্মার
    0.44
     aching
    0.44
     introduces
    0.43
    🥩
    0.43
     slecht
    0.43
     menurunkan
    0.42
    ᓐ
    0.42
     setiap
    0.41
    POSITIVE LOGITS
    H
    0.57
    Education
    0.50
    in
    0.48
    e
    0.46
     Metro
    0.45
     Research
    0.44
    Method
    0.44
    Radio
    0.44
    L
    0.43
     Education
    0.43
    Activations Density 0.003%

    No Known Activations