© 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. 44099
    Prev
    Next
    INDEX
    Explanations

    resulting or preventing changes

    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
     Table
    0.48
     TDP
    0.47
     поговорим
    0.47
     pitanje
    0.47
    ០
    0.47
     Я
    0.46
     Т
    0.46
     २
    0.46
     Lessons
    0.45
     पुत्र
    0.45
    POSITIVE LOGITS
    KBr
    0.45
    Crystal
    0.44
    流
    0.44
     ruffled
    0.41
    Palette
    0.41
    Veronica
    0.41
     resulting
    0.40
    FormControl
    0.39
    되고
    0.39
     ruffle
    0.39
    Activations Density 0.003%

    No Known Activations