© 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. 11005
    Prev
    Next
    INDEX
    Explanations

    new items and next steps

    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
    ड़ों
    0.42
    فاء
    0.39
    îne
    0.38
     አይደለም
    0.38
    Deterministic
    0.38
    ឃ
    0.38
    deterministic
    0.38
    ỗ
    0.38
    ♰
    0.38
     RÉ
    0.37
    POSITIVE LOGITS
     new
    1.95
     neuen
    1.88
     নতুন
    1.86
     새로운
    1.84
     nuovi
    1.83
     nuevos
    1.81
     nieuwe
    1.80
     новых
    1.80
     nuevas
    1.76
     nuove
    1.72
    Activations Density 0.250%

    No Known Activations