© 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. 18667
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    ター
    0.47
     Vaill
    0.42
     ժ
    0.41
     Bailly
    0.39
    gulpfile
    0.38
    坡
    0.38
     کمار
    0.38
    庤
    0.38
    revalidator
    0.38
     ል
    0.38
    POSITIVE LOGITS
     all
    0.39
     उड़ा
    0.38
    ิศ
    0.38
     is
    0.37
     waxes
    0.37
     Espresso
    0.36
     shading
    0.36
     string
    0.36
     tô
    0.36
    Ô
    0.36
    Activations Density 0.003%

    No Known Activations