© 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. 108405
    Prev
    Next
    INDEX
    Explanations

    form validation controls

    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
    Pis
    -0.81
    simas
    -0.73
    gląda
    -0.72
    deo
    -0.71
    alas
    -0.69
     Pis
    -0.69
    тиков
    -0.68
    Ŋ
    -0.68
     variables
    -0.67
     漢
    -0.67
    POSITIVE LOGITS
     control
    0.97
    EMPT
    0.88
    Validators
    0.84
     Validator
    0.83
     Control
    0.79
    控件
    0.76
     Cristi
    0.75
     validators
    0.74
    âme
    0.73
    touched
    0.73
    Activations Density 0.015%

    No Known Activations