© 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. 109677
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

    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
    这一
    -0.91
    自行
    -0.77
     these
    -0.77
    相同
    -0.73
     zwe
    -0.72
    assis
    -0.71
     abzu
    -0.70
    Surname
    -0.70
    強い
    -0.69
     userSchema
    -0.69
    POSITIVE LOGITS
     the
    1.09
     både
    1.03
     hecho
    0.88
     their
    0.87
    höhe
    0.83
     Versions
    0.82
    ("}\
    0.82
    
    0.81
    accesorios
    0.79
     setiap
    0.78
    Activations Density 0.224%

    No Known Activations