© 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. 13422
    Prev
    Next
    INDEX
    Explanations

    equation or equations

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

    equations, punctuation

    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
    BySize
    0.46
    SystemCall
    0.44
    டக்கலை
    0.44
    Tabpage
    0.44
     பாது
    0.43
    Raquete
    0.42
    RenderTarget
    0.41
    󰀄
    0.41
    欤
    0.41
     categoryService
    0.40
    POSITIVE LOGITS
     Equation
    0.66
     equations
    0.66
     Equations
    0.66
     Eqs
    0.64
     equation
    0.57
     eqn
    0.54
     ecuaciones
    0.53
    equations
    0.53
    Equations
    0.52
     Eq
    0.50
    Activations Density 0.001%

    No Known Activations