© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200393
    Prev
    Next
    INDEX
    Explanations

    certain elements

    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
    ;
    0.53
    Q
    0.48
    َّ
    0.47
     ıs
    0.45
    ایل
    0.44
    َص
    0.44
    َا
    0.43
     optio
    0.43
    冋
    0.43
     reflections
    0.42
    POSITIVE LOGITS
    úblic
    0.44
     Né
    0.41
     Palmer
    0.39
    lé
    0.38
     Stamps
    0.38
     entdecken
    0.38
    ಾನೆ
    0.38
    gé
    0.38
     좋을
    0.37
    藪
    0.37
    Activations Density 0.002%

    No Known Activations