© 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. 92092
    Prev
    Next
    INDEX
    Explanations

    content prompts and themes

    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
    ività
    0.43
    邏
    0.41
     Zac
    0.39
    urbance
    0.38
     écran
    0.38
    濯
    0.37
    ení
    0.37
     supplements
    0.37
    ıc
    0.37
     stoichiometry
    0.37
    POSITIVE LOGITS
    FIED
    0.47
     интерес
    0.46
    }]{
    0.46
    AND
    0.45
    ULF
    0.45
    FIELD
    0.44
    বৃন্দ
    0.44
    AVER
    0.44
    ADOW
    0.44
     границ
    0.43
    Activations Density 0.015%

    No Known Activations