© 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. 90839
    Prev
    Next
    INDEX
    Explanations

    front line or first line

    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
    aseous
    -0.79
    спу
    -0.73
    bgColor
    -0.73
    蛎
    -0.71
    OfWeek
    -0.69
    gató
    -0.68
    sobí
    -0.68
    partials
    -0.68
    asco
    -0.68
     الذات
    -0.68
    POSITIVE LOGITS
     front
    5.53
     frontline
    4.81
    front
    4.34
    Front
    3.88
     Front
    3.69
    FRONT
    3.58
     FRONT
    3.28
     fronts
    2.64
     frontend
    2.56
    フロント
    2.47
    Activations Density 0.072%

    No Known Activations