© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31831
    Prev
    Next
    INDEX
    Explanations

    filepath and path usage

    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
     Inference
    0.39
     Bos
    0.36
     RuntimeError
    0.35
     நிற
    0.33
     ange
    0.33
     inference
    0.33
     #-
    0.33
     внимания
    0.33
     inadequ
    0.32
     laten
    0.32
    POSITIVE LOGITS
    relative
    0.52
    Relative
    0.44
    这份
    0.43
    ၂
    0.43
     relative
    0.43
    Absolute
    0.42
     Relative
    0.42
    absolute
    0.42
    दिनी
    0.42
     कट्टर
    0.42
    Activations Density 0.000%

    No Known Activations