© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118285
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    postolic
    -1.10
     ľudí
    -1.08
     flera
    -1.01
     isoli
    -1.00
    wiegend
    -0.99
    ⟺
    -0.98
    soit
    -0.95
     creando
    -0.95
     Memoriam
    -0.95
     リュック
    -0.94
    POSITIVE LOGITS
     a
    5.13
     seorang
    3.41
     an
    3.17
     someone
    2.63
    一个
    2.58
     einem
    2.34
    一名
    2.30
     một
    2.27
    一个人
    2.23
     ஒரு
    2.20
    Activations Density 0.291%

    No Known Activations