© 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. 47647
    Prev
    Next
    INDEX
    Explanations

    questions and specific terms

    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
     on
    -1.02
     by
    -0.92
     here
    -0.89
     before
    -0.84
     now
    -0.84
     hardly
    -0.81
     mừng
    -0.81
     using
    -0.80
    มา
    -0.79
     soon
    -0.78
    POSITIVE LOGITS
    
    0.91
    Stap
    0.90
    胄
    0.88
    תיים
    0.86
    ssn
    0.86
    ində
    0.85
    Whether
    0.85
    .³
    0.85
    Why
    0.83
    cay
    0.83
    Activations Density 0.000%

    No Known Activations