© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    more descriptive word

    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
     wichtigsten
    -1.30
    举动
    -1.28
    heds
    -1.22
     somewhat
    -1.16
    焌
    -1.15
     більш
    -1.11
     большого
    -1.10
     ホルダー
    -1.09
    Masukkan
    -1.09
     ***!
    -1.09
    POSITIVE LOGITS
     than
    3.63
     of
    3.08
     pronounced
    1.30
     options
    1.30
     frequent
    1.27
    Than
    1.27
    than
    1.26
     efficient
    1.19
     stringent
    1.16
     intense
    1.15
    Activations Density 0.054%

    No Known Activations