© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31705
    Prev
    Next
    INDEX
    Explanations

    unknown things

    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_16_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
     a
    1.07
    ن
    1.06
    。</
    1.02
    ية
    0.93
    。\
    0.89
    。
    0.86
    冋
    0.86
    ட்சத்திர
    0.84
    ፣
    0.84
    ي
    0.82
    POSITIVE LOGITS
     for
    1.07
     with
    1.01
     scrutin
    0.89
    AY
    0.86
     reorgan
    0.86
    ı
    0.80
    Unknown
    0.78
    Z
    0.77
     holiday
    0.77
    ED
    0.76
    Activations Density 0.003%

    No Known Activations