© 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. 116831
    Prev
    Next
    INDEX
    Explanations

    height

    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
    诊断
    -0.76
    Tau
    -0.75
    맺
    -0.69
    fct
    -0.68
    ppc
    -0.67
    getParameters
    -0.65
     راحتی
    -0.65
    iaj
    -0.65
    SOC
    -0.64
    wala
    -0.64
    POSITIVE LOGITS
     height
    1.32
    昇
    1.27
     Height
    1.23
    height
    1.16
    HEIGHT
    1.14
    Height
    1.12
     desk
    1.06
     riser
    1.03
     raises
    1.02
     heights
    1.01
    Activations Density 0.007%

    No Known Activations