© 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. 15103
    Prev
    Next
    INDEX
    Explanations

    Castle Island

    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
     πι
    0.50
    λιο
    0.46
     प्रा
    0.44
    腳
    0.43
    aisen
    0.42
     subparagraph
    0.41
     ρο
    0.41
    ГА
    0.41
     яви
    0.41
    現象
    0.41
    POSITIVE LOGITS
     true
    0.49
     Tattoo
    0.46
     सब्सक्राइब
    0.46
    ىلى
    0.45
     True
    0.44
    जूद
    0.44
     Single
    0.44
    屿
    0.44
     avocados
    0.43
     Ott
    0.43
    Activations Density 0.002%

    No Known Activations