© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81244
    Prev
    Next
    INDEX
    Explanations

    transitional html doctype

    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
     should
    -0.94
     their
    -0.94
     previamente
    -0.84
     elt
    -0.83
     öns
    -0.83
    गो
    -0.82
    pieza
    -0.80
    uParam
    -0.79
     usually
    -0.79
    」。
    -0.79
    POSITIVE LOGITS
    DataAnnotations
    1.19
    namt
    1.05
    ecycle
    1.02
     HttpNotFound
    1.01
    IActionResult
    1.01
    migrationBuilder
    0.95
    TagHelper
    0.95
    都不知道
    0.93
    してみた
    0.93
    がある
    0.92
    Activations Density 0.003%

    No Known Activations