© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31023
    Prev
    Next
    INDEX
    Explanations

    lengths in mm and cm

    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
    lında
    -0.82
    colta
    -0.81
    weist
    -0.81
    PostInfinity
    -0.79
     gallon
    -0.78
     MILE
    -0.78
     bucket
    -0.78
     strconv
    -0.77
    forty
    -0.76
    Feet
    -0.75
    POSITIVE LOGITS
    mm
    2.70
     mm
    2.64
     millimeters
    2.03
     millimeter
    1.96
     мм
    1.85
    毫米
    1.50
    MM
    1.49
    millimeters
    1.41
     MM
    1.39
     cm
    1.22
    Activations Density 0.055%

    No Known Activations