© 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. 58780
    Prev
    Next
    INDEX
    Explanations

    ivar, 1, 2,

    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
    вайтесь
    -0.73
    UNIX
    -0.72
    đen
    -0.70
    갯
    -0.70
    Deactivate
    -0.68
    distribution
    -0.68
    escence
    -0.68
    certificates
    -0.67
    pounds
    -0.65
    MUX
    -0.65
    POSITIVE LOGITS
     lobes
    0.71
     Chính
    0.68
    ivar
    0.65
     Pome
    0.64
     Burrell
    0.63
    yka
    0.63
     swabs
    0.62
     Aftermath
    0.62
    erts
    0.61
     cigar
    0.61
    Activations Density 0.111%

    No Known Activations