© 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. 86786
    Prev
    Next
    INDEX
    Explanations

    correspondence and authors

    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
    ICAS
    -0.77
    jän
    -0.75
     сочета
    -0.73
     спла
    -0.72
    marginVertical
    -0.72
    dą
    -0.71
    pheric
    -0.71
     Connectors
    -0.70
    LEAF
    -0.69
     Denny
    -0.69
    POSITIVE LOGITS
     correspondence
    5.41
    correspond
    4.16
    Correspondence
    4.16
     Correspondence
    4.13
     correspond
    3.70
     CORRESPOND
    3.52
     correspondance
    3.25
     corresponded
    3.14
     correspondents
    3.05
     Correspond
    3.02
    Activations Density 0.042%

    No Known Activations