© 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-262K
    7. 203545
    Prev
    Next
    INDEX
    Explanations

    categories 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-it/resid_post/layer_31_width_262k_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
     計算
    0.45
    imut
    0.44
     INDUST
    0.44
     곱
    0.43
    ಂಗ್ರೆ
    0.43
    alimentation
    0.43
     `=
    0.42
     calcul
    0.42
    нома
    0.42
     zroz
    0.42
    POSITIVE LOGITS
     been
    0.48
    或是
    0.47
    در
    0.47
     কিংবা
    0.43
    王
    0.43
    ტ
    0.43
    的对象
    0.42
     Licht
    0.42
    阊
    0.41
     sowie
    0.41
    Activations Density 0.007%

    No Known Activations