© 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. 49063
    Prev
    Next
    INDEX
    Explanations

    Projects, admin, credentials, James, Tired

    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
    brasil
    -0.78
     Maestro
    -0.72
    tj
    -0.71
    طع
    -0.70
    נְ
    -0.68
    grunns
    -0.66
    vw
    -0.65
    琀
    -0.65
    谅
    -0.65
     Cher
    -0.64
    POSITIVE LOGITS
    Projects
    0.93
     projets
    0.85
    koord
    0.83
    ＞
    0.82
    Domain
    0.82
     PROJECT
    0.81
     Projects
    0.79
     проек
    0.79
    sieu
    0.79
     feit
    0.79
    Activations Density 0.008%

    No Known Activations