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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118798
    Prev
    Next
    INDEX
    Explanations

    cre, Cre, Kre start

    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
     reigned
    -0.77
    tomas
    -0.76
    ждены
    -0.76
    attaa
    -0.76
     attenuated
    -0.75
    富山
    -0.74
    فایل
    -0.73
    getDrawable
    -0.73
    Interactor
    -0.71
    evich
    -0.71
    POSITIVE LOGITS
     Cre
    1.13
     cre
    0.97
    Cre
    0.90
    クレ
    0.81
     Kre
    0.76
     urodz
    0.71
    cre
    0.70
     crepe
    0.70
     entendi
    0.68
     sababu
    0.68
    Activations Density 0.024%

    No Known Activations