© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91959
    Prev
    Next
    INDEX
    Explanations

    documentation, code, or lists

    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
    यू
    0.47
     работой
    0.47
    㓦
    0.45
     পরও
    0.44
    珹
    0.42
     certificación
    0.42
    撰
    0.42
    現在は
    0.42
    颖
    0.42
    Año
    0.41
    POSITIVE LOGITS
    nil
    0.47
     astronomers
    0.46
     ballots
    0.46
    kHz
    0.46
     ballistic
    0.45
     conspiracy
    0.44
     vaccination
    0.44
     neighboring
    0.44
     facilitation
    0.43
     superconducting
    0.43
    Activations Density 0.001%

    No Known Activations