© 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. 18006
    Prev
    Next
    INDEX
    Explanations

    but and contrast statements

    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
    ਦਰ
    0.22
     waarbij
    0.21
    且
    0.21
    **
    0.20
    Wrapper
    0.20
    Variable
    0.19
     publiés
    0.19
    🌒
    0.19
     lesquelles
    0.19
    Also
    0.19
    POSITIVE LOGITS
     it
    0.42
     It
    0.31
     это
    0.31
     there
    0.30
     they
    0.29
     यह
    0.29
    there
    0.29
     ისინი
    0.28
     এটা
    0.27
     THEY
    0.27
    Activations Density 0.126%

    No Known Activations