© 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. 32920
    Prev
    Next
    INDEX
    Explanations

    cube faces and sides

    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
    古代
    -0.85
    cahontas
    -0.79
    MSD
    -0.79
    dersfield
    -0.78
    campal
    -0.78
    AAAAAAAA
    -0.76
    طنين
    -0.76
     unim
    -0.74
    继续阅读
    -0.74
    osomes
    -0.74
    POSITIVE LOGITS
     faces
    1.79
     sides
    1.62
     front
    1.59
     face
    1.47
     Faces
    1.34
    faces
    1.30
     Front
    1.27
     FRONT
    1.22
    front
    1.20
     surfaces
    1.16
    Activations Density 0.026%

    No Known Activations