© 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. 107301
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

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

    math topics including quadratic and graphing

    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
     virtue
    0.52
     nave
    0.48
     $\
    0.48
     m
    0.46
     museum
    0.46
     tobacco
    0.46
     steel
    0.45
     preserv
    0.45
     defensa
    0.45
     y
    0.44
    POSITIVE LOGITS
    θε
    0.52
     гр
    0.51
    сторінку
    0.50
     антен
    0.50
    ቁ
    0.48
     телефо
    0.48
    ліза
    0.47
     curviliné
    0.47
     частиц
    0.46
    йно
    0.46
    Activations Density 0.000%

    No Known Activations