© 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. 55675
    Prev
    Next
    INDEX
    Explanations

    pagination context or page editor

    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
     Lie
    0.46
    Lie
    0.44
    desPort
    0.44
    totalPages
    0.44
    页
    0.44
    Pager
    0.43
     Segment
    0.43
     totales
    0.43
    мма
    0.42
    厛
    0.42
    POSITIVE LOGITS
    ći
    0.41
     fiance
    0.41
     size
    0.41
    otid
    0.41
     PCC
    0.38
    plicit
    0.38
    ine
    0.38
    iable
    0.37
    这个时候
    0.37
     agency
    0.37
    Activations Density 0.004%

    No Known Activations