© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10561
    Prev
    Next
    INDEX
    Explanations

    academic and professional topics

    np_acts-logits-general · gemini-2.5-flash-lite

    academic subjects and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    THF
    0.45
    J
    0.41
    পুর
    0.39
    alma
    0.39
    defer
    0.38
    SUM
    0.38
    বার
    0.38
     partito
    0.38
    UIL
    0.38
    বাই
    0.38
    POSITIVE LOGITS
    热门
    0.47
     topics
    0.47
     Topics
    0.47
     관련
    0.46
    밌
    0.45
    相关
    0.44
     beheld
    0.44
     പോലുള്ള
    0.43
     टिप्स
    0.42
     बखूबी
    0.42
    Activations Density 0.002%

    No Known Activations