© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12236
    Prev
    Next
    INDEX
    Explanations

    approximately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ไม่
    -1.11
    มี
    -1.09
     and
    -1.07
     (!__
    -1.04
    为了
    -1.04
    以前
    -1.02
    ทำ
    -1.01
    ১
    -0.98
    原因
    -0.97
    生活中
    -0.96
    POSITIVE LOGITS
     roughly
    1.62
     approximately
    1.47
    roughly
    1.39
     примерно
    1.25
    Rough
    1.17
     ongeveer
    1.15
    approximately
    1.13
     लगभग
    1.13
     Roughly
    1.13
    だいたい
    1.07
    Activations Density 0.035%

    No Known Activations