© 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. 97841
    Prev
    Next
    INDEX
    Explanations

    weather information and districts

    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
     etap
    -0.71
    containsKey
    -0.69
     Né
    -0.69
     Ophelia
    -0.67
    önes
    -0.67
    長野
    -0.67
    喝酒
    -0.66
     Dartmouth
    -0.66
    
    -0.65
     Hitchcock
    -0.65
    POSITIVE LOGITS
    wok
    0.71
     DOI
    0.70
     scissor
    0.70
    quid
    0.70
     Flax
    0.69
    cisi
    0.69
    cab
    0.67
     Pact
    0.66
    CIC
    0.65
    Fingerprint
    0.65
    Activations Density 0.092%

    No Known Activations