© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    types of 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
    butadiene
    0.29
    绺
    0.29
    DataXYZ
    0.29
    CommonAncestor
    0.29
    птовалю
    0.28
    omorphisms
    0.28
    ajjati
    0.28
     singleRun
    0.28
    এক
    0.27
     थरूर
    0.27
    POSITIVE LOGITS
    6
    0.35
    7
    0.28
     Kindern
    0.28
    3
    0.28
    2
    0.27
    -,
    0.27
     rup
    0.27
     and
    0.26
     v
    0.26
     konci
    0.26
    Activations Density 1.034%

    No Known Activations