© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78585
    Prev
    Next
    INDEX
    Explanations

    java imports

    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
     again
    -1.37
     during
    -1.26
     Without
    -1.23
     when
    -1.23
     Again
    -1.16
     Although
    -1.16
    this
    -1.14
     without
    -1.13
     Since
    -1.11
    見えます
    -1.09
    POSITIVE LOGITS
    スポンサーリンク
    1.10
     avantages
    1.09
     bienven
    1.08
     java
    1.05
    <blockquote>
    1.03
     champignons
    1.02
     архив
    1.02
     inox
    1.02
     mètres
    1.01
    %。
    1.00
    Activations Density 0.024%

    No Known Activations