© 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. 10-GEMMASCOPE-RES-131K
    7. 66352
    Prev
    Next
    INDEX
    Explanations

    html alignment attributes

    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_10/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
    If
    -2.39
    When
    -2.38
    While
    -2.28
    There
    -2.25
    Even
    -2.23
    Many
    -2.17
     indicates
    -2.08
    ts
    -2.05
     requires
    -2.02
    y
    -1.99
    POSITIVE LOGITS
     ſie
    2.30
     polska
    2.08
     elegante
    2.08
    
    2.06
     temat
    2.06
     amd
    2.06
     России
    1.95
    ität
    1.95
     sumptuous
    1.95
     abstrak
    1.92
    Activations Density 0.014%

    No Known Activations