© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60145
    Prev
    Next
    INDEX
    Explanations

    financial statements and reporting

    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
    irms
    -0.78
     continú
    -0.75
     уточ
    -0.74
     unirse
    -0.74
    ПП
    -0.74
    来越
    -0.74
     conducteur
    -0.74
    ListItem
    -0.73
    ترا
    -0.73
    бно
    -0.72
    POSITIVE LOGITS
     statements
    1.67
     statement
    1.33
    statements
    1.31
     reporting
    1.31
     position
    1.23
    Statements
    1.20
    statement
    1.19
    reporting
    1.16
     STATEMENTS
    1.15
     Statements
    1.14
    Activations Density 0.020%

    No Known Activations