© 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-65K
    7. 47840
    Prev
    Next
    INDEX
    Explanations

    package installation commands

    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_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
     должности
    0.41
    醪
    0.39
    azawa
    0.39
    眅
    0.39
    រូប
    0.38
    大气
    0.38
    ına
    0.38
     तनु
    0.38
     intestino
    0.38
    氐
    0.37
    POSITIVE LOGITS
    animations
    0.38
     screens
    0.37
     Somalia
    0.37
     পিটার
    0.37
     rely
    0.37
     relying
    0.37
     bridged
    0.36
     Screens
    0.36
     animations
    0.35
     childish
    0.35
    Activations Density 0.003%

    No Known Activations