© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2353
    Prev
    Next
    INDEX
    Explanations

    fractions and mathematical equations

    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_40_width_65k_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
     ორგანო
    0.52
    Gosudarstvennyj
    0.50
    manız
    0.48
    鹘
    0.48
    EnglishMarks
    0.46
     결혼
    0.45
    Sebastian
    0.45
     المتحدة
    0.44
     হানাদার
    0.44
    晠
    0.44
    POSITIVE LOGITS
     fraction
    1.82
     fractions
    1.76
    frac
    1.73
     Fraction
    1.65
     frac
    1.59
    Fraction
    1.57
     fractional
    1.49
    mfrac
    1.45
    fraction
    1.44
     Fractions
    1.44
    Activations Density 0.252%

    No Known Activations