© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206807
    Prev
    Next
    INDEX
    Explanations

    addition and mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legyen
    0.43
    سال
    0.42
    １
    0.39
     কূট
    0.39
    кут
    0.38
     没有
    0.37
     خواب
    0.37
     década
    0.37
     bě
    0.37
     ialah
    0.37
    POSITIVE LOGITS
    owań
    0.43
    now
    0.42
    [%
    0.41
     instit
    0.40
    த்தூர்
    0.39
    oi
    0.39
    fortunately
    0.39
    𝙢
    0.38
    ti
    0.38
    practices
    0.37
    Activations Density 0.000%

    No Known Activations