© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81087
    Prev
    Next
    INDEX
    Explanations

    aspect ratio

    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
     nyug
    0.51
    Expenses
    0.44
    Joe
    0.43
    医療
    0.43
    Histor
    0.42
    任意
    0.42
    Jeg
    0.42
    ၻ
    0.42
    Det
    0.41
    Anyway
    0.41
    POSITIVE LOGITS
    વાની
    0.46
    áct
    0.45
     scolded
    0.44
    стами
    0.42
    长大
    0.42
    ógica
    0.41
    entesque
    0.41
     возраста
    0.41
    kadang
    0.41
     alumin
    0.41
    Activations Density 0.010%

    No Known Activations