© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109726
    Prev
    Next
    INDEX
    Explanations

    legal acts and statutes

    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
     iniziato
    -0.84
     ścian
    -0.82
     Gewinner
    -0.78
     خونه
    -0.75
    是中国
    -0.74
     savant
    -0.74
    displayquote
    -0.74
    Terug
    -0.73
    Groetjes
    -0.73
    していく
    -0.73
    POSITIVE LOGITS
     Act
    1.06
    runtime
    1.06
     парла
    1.00
     statute
    0.99
    Act
    0.96
     repeal
    0.93
    Stat
    0.86
     стату
    0.85
     runtime
    0.84
     consolidating
    0.83
    Activations Density 0.019%

    No Known Activations