© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119127
    Prev
    Next
    INDEX
    Explanations

    FIG. and numbers

    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
     udara
    -0.82
    穢
    -0.77
    。《
    -0.76
     not
    -0.74
     прово
    -0.73
     methods
    -0.72
     empuj
    -0.71
    農
    -0.71
     SqlConnection
    -0.71
    ByUserId
    -0.71
    POSITIVE LOGITS
     PATENT
    0.95
     остается
    0.88
    <eos>
    0.85
    patent
    0.84
    fié
    0.84
     drm
    0.82
    bours
    0.81
    Unnamed
    0.81
    tion
    0.78
    みると
    0.78
    Activations Density 0.023%

    No Known Activations