© 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. 107871
    Prev
    Next
    INDEX
    Explanations

    file header comments

    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
     In
    -1.03
     (
    -1.02
     in
    -1.00
     Check
    -0.99
     O
    -0.95
     E
    -0.93
     differ
    -0.91
    Check
    -0.89
     J
    -0.88
     At
    -0.88
    POSITIVE LOGITS
    ↵
    1.23
    Kritik
    1.12
    selben
    1.09
    aktivi
    1.05
     clô
    1.05
    klart
    1.04
     écou
    1.03
     écl
    1.00
     faciliter
    0.99
    Faktor
    0.99
    Activations Density 0.010%

    No Known Activations