© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59018
    Prev
    Next
    INDEX
    Explanations

    words starting with Comp

    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
     nghỉ
    -0.80
     Mor
    -0.76
    벡
    -0.73
    闹
    -0.73
     注意
    -0.71
    ayant
    -0.71
     ancho
    -0.70
     suced
    -0.70
    ayı
    -0.70
     tavern
    -0.70
    POSITIVE LOGITS
     COMP
    1.82
     Comp
    1.80
    comp
    1.73
     comp
    1.66
    Comp
    1.55
    COMP
    1.52
     компа
    1.32
    komp
    1.30
    comps
    1.30
     komp
    1.24
    Activations Density 0.013%

    No Known Activations