© 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. 107095
    Prev
    Next
    INDEX
    Explanations

    method definitions

    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
    出了一
    -1.08
     also
    -0.87
    Также
    -0.86
     although
    -0.85
    耻
    -0.85
     также
    -0.83
     aunque
    -0.82
     such
    -0.82
     denominado
    -0.82
    hecimento
    -0.82
    POSITIVE LOGITS
    ↵
    1.65
     then
    1.28
     então
    1.14
     göm
    1.09
    Then
    1.09
     dök
    1.05
    )$;
    1.04
    редиенты
    1.02
    imantan
    1.01
     następnie
    1.00
    Activations Density 0.032%

    No Known Activations