© 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. 11071
    Prev
    Next
    INDEX
    Explanations

    misc and miscellaneous items

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

    effort levels

    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
    🚜
    0.48
    🍠
    0.46
     छह
    0.45
     шесть
    0.43
    芒果
    0.43
     гипсо
    0.42
    🐠
    0.42
    🥐
    0.42
    গরে
    0.41
     новые
    0.41
    POSITIVE LOGITS
     another
    0.48
     both
    0.42
     misc
    0.41
     Misc
    0.40
     Bell
    0.40
     Miscellaneous
    0.40
     Mad
    0.40
     Bed
    0.39
     Nai
    0.39
     Another
    0.38
    Activations Density 0.117%

    No Known Activations