© 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. 22-GEMMASCOPE-RES-131K
    7. 12140
    Prev
    Next
    INDEX
    Explanations

    hard followed by specific nouns

    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_22/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
     अन्य
    -1.09
     azok
    -1.02
    -
    -1.00
     colorés
    -1.00
    </sub>
    -0.96
    度に
    -0.96
    chica
    -0.94
     объема
    -0.93
     as
    -0.92
    بیش
    -0.92
    POSITIVE LOGITS
    <bos>
    1.22
    ఝ
    1.20
    鬟
    0.98
    러나
    0.97
    必須
    0.96
     talleres
    0.94
    meteries
    0.91
    の新
    0.90
     リブ
    0.90
    ยว
    0.90
    Activations Density 0.070%

    No Known Activations