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. 191
    Prev
    Next
    INDEX
    Explanations

    Raiders, Raider, raiding

    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
    -3.27
    When
    -3.22
    '
    -3.05
    For
    -2.98
    when
    -2.92
    1
    -2.89
    <strong>
    -2.84
    To
    -2.83
    Even
    -2.83
    </h2>
    -2.78
    POSITIVE LOGITS
    鼍
    3.64
    蛲
    3.33
    archiwizowane
    3.23
    觏
    3.19
    耵
    3.14
    
    3.03
    罴
    3.03
    裥
    2.91
    ⎔
    2.88
     帅气
    2.86
    Activations Density 0.002%

    No Known Activations