© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    airborne noise

    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
     Tofu
    -0.75
     jól
    -0.74
     kinematics
    -0.73
     Ngoài
    -0.70
    Fabri
    -0.69
     Commer
    -0.68
     Bogen
    -0.68
     Dome
    -0.66
    スズキ
    -0.66
    Bernie
    -0.65
    POSITIVE LOGITS
     airborne
    1.35
     flanking
    1.10
     Airborne
    1.06
    STC
    0.92
    ルド
    0.86
     STC
    0.84
    flan
    0.82
     flan
    0.82
     Flan
    0.81
    oscopic
    0.81
    Activations Density 0.009%

    No Known Activations