© 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. 48692
    Prev
    Next
    INDEX
    Explanations

    used to

    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
     largas
    -1.05
    advised
    -0.98
     jeunes
    -0.98
    البته
    -0.97
    Revis
    -0.95
     touristes
    -0.95
     COMERC
    -0.94
     TAMB
    -0.94
     favorito
    -0.94
    سوال
    -0.94
    POSITIVE LOGITS
     when
    2.80
    when
    1.74
     cuando
    1.69
     to
    1.66
     whenever
    1.64
     during
    1.49
     by
    1.46
     quando
    1.41
    When
    1.40
     if
    1.39
    Activations Density 0.060%

    No Known Activations