© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107790
    Prev
    Next
    INDEX
    Explanations

    words starting with 'co'

    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
    問題は
    -0.77
     equilibrium
    -0.77
    Replication
    -0.76
    เอง
    -0.67
     Pare
    -0.67
     pare
    -0.66
     bush
    -0.66
     mạnh
    -0.66
    銘
    -0.65
    調査
    -0.65
    POSITIVE LOGITS
    ^*)
    0.85
    вока
    0.83
     ricor
    0.82
     ")");
    0.79
     국
    0.78
     subray
    0.77
     entour
    0.76
    Tian
    0.74
     débat
    0.74
    ultati
    0.73
    Activations Density 0.066%

    No Known Activations