© 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. 70015
    Prev
    Next
    INDEX
    Explanations

    official statements

    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
     meta
    -0.79
     durante
    -0.79
     gray
    -0.76
     ID
    -0.75
    tdc
    -0.75
    theorem
    -0.74
     halten
    -0.73
     země
    -0.73
     Gray
    -0.72
    aggressive
    -0.72
    POSITIVE LOGITS
     statement
    1.28
    statement
    0.99
    Statement
    0.98
     signed
    0.96
     Statement
    0.92
    🆚
    0.91
     reaction
    0.90
    Signed
    0.87
     unsigned
    0.86
     Publicity
    0.86
    Activations Density 0.009%

    No Known Activations