© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45355
    Prev
    Next
    INDEX
    Explanations

    hold on, off, onto, up

    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
     ਨਾਲ
    -0.94
    viseur
    -0.91
    rieux
    -0.88
    courtesy
    -0.85
    chevêque
    -0.85
    Kontrola
    -0.83
    ûr
    -0.83
    malige
    -0.82
     Ông
    -0.82
    september
    -0.82
    POSITIVE LOGITS
     onto
    1.94
     up
    1.71
     on
    1.41
     a
    1.33
     out
    1.27
     back
    1.18
     grud
    1.15
     off
    1.12
     forth
    1.12
    out
    1.09
    Activations Density 0.008%

    No Known Activations