© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57631
    Prev
    Next
    INDEX
    Explanations

    subdivisions and sections

    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
    chè
    -0.92
    我们的
    -0.81
     tidigare
    -0.80
    Chapter
    -0.80
    ピング
    -0.80
     préférence
    -0.78
    伴
    -0.77
     نقط
    -0.77
     términos
    -0.76
    udert
    -0.76
    POSITIVE LOGITS
     sub
    2.48
    sub
    2.05
     Sub
    1.84
    Sub
    1.78
     subsection
    1.55
     this
    1.47
     SUB
    1.43
    SUB
    1.36
     суб
    1.30
     subdivision
    1.21
    Activations Density 0.017%

    No Known Activations