© 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. 34-GEMMASCOPE-RES-131K
    7. 109743
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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_34/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
     Twenty
    -1.30
     TWENTY
    -1.15
     twenty
    -1.10
     vingt
    -1.09
    Twenty
    -1.05
     Eighteen
    -1.00
     twenties
    -0.98
     Nineteen
    -0.97
     XXIII
    -0.96
     Sixteen
    -0.93
    POSITIVE LOGITS
    6
    1.67
    7
    1.63
    8
    1.42
    5
    1.27
     ۶
    1.24
     ۸
    1.17
     sixty
    1.14
     seven
    1.11
     ۷
    1.09
     six
    1.05
    Activations Density 0.071%

    No Known Activations