© 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. 138
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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
     prototyping
    0.32
     conformal
    0.31
    `-
    0.31
     microp
    0.30
    :`
    0.30
     bytes
    0.30
     scalable
    0.30
     configuration
    0.29
    :")
    0.29
     regex
    0.29
    POSITIVE LOGITS
     Mr
    0.43
     himself
    0.39
     Ethan
    0.39
     Grace
    0.38
     Jamie
    0.36
     Christian
    0.36
     Robert
    0.36
     Lionel
    0.36
     Noah
    0.36
     Thomas
    0.35
    Activations Density 0.130%

    No Known Activations