© 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. 73367
    Prev
    Next
    INDEX
    Explanations

    without restriction or warranty

    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
     instead
    -1.27
     not
    -1.27
     that
    -1.23
     with
    -1.11
     rather
    -1.04
     when
    -0.94
     вместо
    -0.92
    什么样的
    -0.91
    ではなく
    -0.91
    üedad
    -0.88
    POSITIVE LOGITS
     or
    1.77
     nor
    1.45
    หรือ
    1.27
    ใด
    1.16
    或
    1.07
    任何
    1.02
     whatsoever
    1.01
     fanfare
    0.98
     aucune
    0.97
     versehen
    0.96
    Activations Density 0.122%

    No Known Activations