Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 282
    Prev
    Next
    INDEX
    Explanations

    computer programming and mathematics

    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_10/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
    _{
    -2.95
    
    -2.86
    ными
    -2.42
    er
    -2.42
    N
    -2.38
    舛
    -2.33
    塤
    -2.30
    !");
    -2.23
    们的
    -2.23
    
    -2.22
    POSITIVE LOGITS
    }$
    3.63
    [
    3.25
    筇
    2.72
    -"
    2.70
    </sub>
    2.66
    ("
    2.63
    ...
    2.45
    </th>
    2.41
    ";
    
    2.39
    嗶
    2.39
    Activations Density 0.001%

    No Known Activations