© 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. 31-GEMMASCOPE-2-RES-65K
    7. 6470
    Prev
    Next
    INDEX
    Explanations

    hacksaw, capybaras, Key

    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_31_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
    ጣጠ
    0.48
    
    0.48
    currentComponent
    0.47
    亓
    0.46
     לפני
    0.46
    螞
    0.46
    郯
    0.46
    薜
    0.45
    葶
    0.45
    щении
    0.44
    POSITIVE LOGITS
    1
    0.59
    ↵
    0.50
    스
    0.49
    [
    0.47
     the
    0.45
     encounters
    0.44
    6
    0.44
    <
    0.43
    고
    0.43
     monitors
    0.43
    Activations Density 0.007%

    No Known Activations