© 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. 32014
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and questions

    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
    ита
    -0.73
    ➽
    -0.72
    ground
    -0.70
     الساعة
    -0.69
    yoruz
    -0.69
    druid
    -0.68
    Empleado
    -0.67
     tussen
    -0.66
    рт
    -0.66
     Ground
    -0.65
    POSITIVE LOGITS
     faces
    1.38
     face
    1.30
     Faces
    1.20
     Face
    1.02
    faces
    1.02
    Face
    1.02
     vertices
    0.97
    face
    0.92
    Faces
    0.88
     edges
    0.85
    Activations Density 0.033%

    No Known Activations