© 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. 91026
    Prev
    Next
    INDEX
    Explanations

    example, published, synonyms

    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
    ForEach
    -0.84
     statuses
    -0.80
    ellees
    -0.72
     Auger
    -0.71
     killing
    -0.71
    status
    -0.70
    Dora
    -0.69
     status
    -0.69
     Carlson
    -0.69
    ulen
    -0.68
    POSITIVE LOGITS
     examples
    0.87
    scott
    0.76
    Examples
    0.74
    examples
    0.70
    Scott
    0.68
     example
    0.68
    ρίς
    0.66
    och
    0.66
     Trie
    0.66
    Trie
    0.65
    Activations Density 0.030%

    No Known Activations