© 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. 31-GEMMASCOPE-2-RES-65K
    7. 29597
    Prev
    Next
    INDEX
    Explanations

    within hours

    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_31_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
    áci
    0.50
    ;
    0.49
     palo
    0.46
    treme
    0.45
     ujar
    0.45
    koliko
    0.44
     kvůli
    0.44
     rampant
    0.43
    royo
    0.43
     fscanf
    0.42
    POSITIVE LOGITS
    𝔀
    0.48
    最终
    0.47
    辂
    0.44
    逐渐
    0.41
    此时
    0.40
    梦想
    0.40
     வெற்றிய
    0.39
     Schönheit
    0.39
    教堂
    0.39
    胜利
    0.38
    Activations Density 0.003%

    No Known Activations