© 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. 64820
    Prev
    Next
    INDEX
    Explanations

    floating things

    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
     القانون
    -0.93
     gérer
    -0.87
     déclar
    -0.86
     NINE
    -0.86
     parere
    -0.86
     Reasonable
    -0.85
     całego
    -0.85
    ১
    -0.84
    什麼
    -0.84
     moistened
    -0.84
    POSITIVE LOGITS
     floating
    2.63
     Floating
    2.56
     float
    2.41
     floated
    2.30
     Float
    2.23
     floats
    2.19
    Floating
    2.17
    float
    2.17
    floating
    2.16
    浮
    1.96
    Activations Density 0.015%

    No Known Activations