© 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. 31670
    Prev
    Next
    INDEX
    Explanations

    stand up, stand against, stand with

    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
     aihe
    -0.80
    rotum
    -0.80
    bla
    -0.79
    спомина
    -0.75
     понимаю
    -0.75
     struggling
    -0.74
    cana
    -0.74
    frame
    -0.73
    magic
    -0.73
    ppy
    -0.73
    POSITIVE LOGITS
     up
    1.72
     against
    1.41
     firm
    1.20
     by
    1.07
     strong
    1.03
     FIRM
    1.00
     STRONG
    0.97
     Strong
    0.96
     occafion
    0.93
     tall
    0.92
    Activations Density 0.012%

    No Known Activations