© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76253
    Prev
    Next
    INDEX
    Explanations

    sidelines, margins, or fringes

    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
    藕
    -0.66
    kevin
    -0.65
    hanna
    -0.65
    ぼちゃ
    -0.65
    ilak
    -0.63
    lamine
    -0.62
    ffa
    -0.62
    lers
    -0.61
    weiler
    -0.60
     getB
    -0.60
    POSITIVE LOGITS
     sidelines
    5.25
     sideline
    4.38
     sidelined
    2.33
     side
    1.81
    Side
    1.65
     Side
    1.63
     margins
    1.63
     SID
    1.53
     fringes
    1.48
    side
    1.41
    Activations Density 0.014%

    No Known Activations