© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103169
    Prev
    Next
    INDEX
    Explanations

    signatures and appeals

    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
     плоско
    -0.85
     table
    -0.84
    lorus
    -0.84
     anys
    -0.79
    海外
    -0.79
    讓
    -0.78
    шники
    -0.77
    天王
    -0.77
     ZERO
    -0.75
    RESUMO
    -0.75
    POSITIVE LOGITS
     signatures
    1.33
    Signatures
    1.27
     signature
    1.20
    signature
    1.17
    Signature
    1.13
    signatures
    1.10
    Seal
    1.09
     Signature
    1.09
    SIGNATURE
    1.09
    seal
    1.08
    Activations Density 0.000%

    No Known Activations