© 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. 119020
    Prev
    Next
    INDEX
    Explanations

    Bosnia and related words

    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
    Kamu
    -0.73
     combinaison
    -0.73
     насеље
    -0.72
    Ար
    -0.71
    )!=
    -0.71
    Busy
    -0.71
    Minh
    -0.70
    닭
    -0.69
     رش
    -0.68
    リューム
    -0.67
    POSITIVE LOGITS
     Bos
    1.07
     bos
    1.01
     BOS
    0.98
    BOS
    0.91
     Bosco
    0.91
    Bos
    0.90
    bos
    0.83
     Boss
    0.80
    πω
    0.77
    mmate
    0.76
    Activations Density 0.025%

    No Known Activations