© 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. 117027
    Prev
    Next
    INDEX
    Explanations

    date, Stokes, must

    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
     monitor
    -0.77
    läng
    -0.71
    لمين
    -0.68
    three
    -0.68
    hí
    -0.67
     Events
    -0.66
     falls
    -0.65
    Ꭲ
    -0.65
    monitor
    -0.65
     fall
    -0.64
    POSITIVE LOGITS
    sld
    0.75
     Phnom
    0.74
    ाइट
    0.73
    thod
    0.71
    Bibliografía
    0.66
     CZ
    0.66
     pinball
    0.65
    feiri
    0.65
     Referee
    0.65
     rower
    0.64
    Activations Density 0.059%

    No Known Activations