© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 196
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .com or .org

    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
    \
    0.47
     iter
    0.47
    等
    0.44
     somehow
    0.43
     repeatedly
    0.43
    cli
    0.43
    .
    0.43
    )}\
    0.42
     trit
    0.42
    र्जी
    0.42
    POSITIVE LOGITS
    辎
    0.48
    ưởng
    0.45
    धपुर
    0.45
    Pets
    0.45
    羡
    0.44
    馇
    0.44
    Animals
    0.43
    ewöhn
    0.42
    ırlar
    0.42
     Beasts
    0.42
    Activations Density 0.001%

    No Known Activations