© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134070
    Prev
    Next
    INDEX
    Explanations

    illustrate, outline, describe

    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
    少
    0.43
     peu
    0.42
     தோட்டங்கள்
    0.42
    padStart
    0.42
    ynes
    0.41
    ペース
    0.41
     palvel
    0.40
    のうち
    0.40
     कार्यरत
    0.39
    premises
    0.39
    POSITIVE LOGITS
     faint
    0.39
     avoidance
    0.39
     What
    0.39
     nonchal
    0.38
     ছেলের
    0.37
    所
    0.36
     wounded
    0.36
     jang
    0.36
     laissez
    0.35
     शैली
    0.35
    Activations Density 0.000%

    No Known Activations