© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12674
    Prev
    Next
    INDEX
    Explanations

    expo-media-library

    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_262k_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
     ivvu
    0.45
    шению
    0.41
    誇
    0.40
     guerre
    0.40
    тивних
    0.39
    гих
    0.39
     joined
    0.39
    ക്കുറ
    0.38
    Characteristic
    0.38
    禅
    0.38
    POSITIVE LOGITS
     Expo
    0.63
     Exponential
    0.62
    Expo
    0.57
     exponentially
    0.51
     exponential
    0.49
    expo
    0.49
     Florida
    0.48
    Florida
    0.47
    Exponential
    0.46
     exponencial
    0.46
    Activations Density 0.001%

    No Known Activations