© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63001
    Prev
    Next
    INDEX
    Explanations

    javascript and browser compatibility

    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
    끈
    -0.75
    шкан
    -0.75
    玦
    -0.73
    ਈ
    -0.71
    sibilité
    -0.70
     Salud
    -0.69
    юсь
    -0.69
     Unlock
    -0.66
    ằm
    -0.66
    Alright
    -0.65
    POSITIVE LOGITS
     Blaze
    0.76
    EventHandler
    0.68
     zwing
    0.65
    tiu
    0.64
    FFFFFFFF
    0.64
    否则
    0.63
    handlers
    0.63
    AAS
    0.63
    urez
    0.63
    InRange
    0.62
    Activations Density 0.066%

    No Known Activations