© 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. 2283
    Prev
    Next
    INDEX
    Explanations

    ASOS

    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
    יל
    0.43
    ש
    0.39
    Ч
    0.39
    ז
    0.39
    Й
    0.39
    Все
    0.39
    ר
    0.39
    า
    0.38
    АН
    0.38
    Cada
    0.38
    POSITIVE LOGITS
    0.42
     showcased
    0.34
     Director
    0.33
     aforementioned
    0.33
     proposed
    0.32
     Chair
    0.30
     snacks
    0.30
     User
    0.29
     Beta
    0.29
     Lavender
    0.29
    Activations Density 0.331%

    No Known Activations