© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119207
    Prev
    Next
    INDEX
    Explanations

    Caucasian Sketches

    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
    ناول
    -0.75
    𝑔
    -0.74
     as
    -0.74
    فتح
    -0.73
    posy
    -0.69
     comprehend
    -0.67
     Kamar
    -0.66
    type
    -0.65
     보
    -0.65
     premature
    -0.65
    POSITIVE LOGITS
    teach
    0.81
     Strasse
    0.79
     anciennes
    0.79
    edded
    0.78
     глоба
    0.78
    phous
    0.77
    dreams
    0.77
     saveurs
    0.77
    COO
    0.75
    ($)
    0.75
    Activations Density 0.005%

    No Known Activations