© 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. 31-GEMMASCOPE-2-RES-262K
    4. 17671
    Prev
    Next
    INDEX
    Explanations

    out of bounds or range

    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
     dwóch
    0.54
     będzie
    0.53
     उन्‍हें
    0.52
     gdzie
    0.51
    োধন
    0.51
    碜
    0.51
    ÉT
    0.50
    พื้น
    0.50
     tématu
    0.49
     দূর
    0.48
    POSITIVE LOGITS
     out
    0.96
     of
    0.78
    out
    0.75
     Out
    0.73
     Bounds
    0.67
     bounds
    0.64
    bounds
    0.64
    岕
    0.63
     벗
    0.63
    iv
    0.62
    Activations Density 0.034%

    No Known Activations