© 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. 97811
    Prev
    Next
    INDEX
    Explanations

    signing protocols

    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
     summoning
    -0.72
     droits
    -0.71
     summoned
    -0.71
    keith
    -0.68
     Andrés
    -0.68
    Tester
    -0.67
     telep
    -0.66
    gnal
    -0.66
    onChangeText
    -0.66
     newArray
    -0.66
    POSITIVE LOGITS
    Signature
    0.99
     signature
    0.98
    signature
    0.97
     signed
    0.94
     Signature
    0.93
     Signed
    0.91
     signer
    0.87
     enveloped
    0.87
     signing
    0.86
     signatures
    0.86
    Activations Density 0.037%

    No Known Activations