© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 110550
    Prev
    Next
    INDEX
    Explanations

    technical terms and contexts

    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_40_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
     cross
    0.62
     क्रॉस
    0.61
     CROSS
    0.52
    cross
    0.49
     ক্রস
    0.47
     Cross
    0.47
    クロス
    0.44
    跨
    0.44
    CROSS
    0.44
    tega
    0.43
    POSITIVE LOGITS
     প্রেরণ
    0.39
    Communication
    0.38
     Programming
    0.38
    Technical
    0.37
     डॉन
    0.37
    یو
    0.37
    irmer
    0.37
    Bol
    0.36
     quorum
    0.36
    ˃
    0.36
    Activations Density 0.000%

    No Known Activations