© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11448
    Prev
    Next
    INDEX
    Explanations

    Optimal cut-off coding

    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
     eight
    -1.34
    روابط
    -1.22
     three
    -1.19
     beserta
    -1.13
     at
    -1.13
    harmonie
    -1.13
     seven
    -1.12
     after
    -1.12
     through
    -1.11
     sambil
    -1.09
    POSITIVE LOGITS
    メラ
    1.02
    B
    1.00
    氣
    0.98
    w
    0.97
    h
    0.94
     participer
    0.92
    o
    0.91
    _
    0.91
    en
    0.90
    E
    0.90
    Activations Density 0.002%

    No Known Activations