© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91916
    Prev
    Next
    INDEX
    Explanations

    covered under terms and conditions

    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
    fehlungen
    -0.93
     اداری
    -0.76
    esez
    -0.74
    <%
    -0.74
    onesome
    -0.73
      “
    -0.73
    almaz
    -0.72
    ösungen
    -0.72
    leuchte
    -0.71
    ffective
    -0.71
    POSITIVE LOGITS
     covered
    5.47
    covered
    4.13
     Covered
    3.94
    Covered
    3.89
     COVER
    2.73
     included
    2.31
     protected
    2.30
    COVER
    2.20
     cover
    2.13
     governed
    2.05
    Activations Density 0.148%

    No Known Activations