© 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. 107009
    Prev
    Next
    INDEX
    Explanations

    AC or Ac followed by specific words

    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
     arroyo
    -0.79
    ările
    -0.77
     Secre
    -0.75
    ществует
    -0.75
     CONTRA
    -0.73
    HUS
    -0.72
     Convertible
    -0.72
     Sectors
    -0.71
    ैसे
    -0.70
     molly
    -0.70
    POSITIVE LOGITS
     Zhou
    0.78
    ifolium
    0.75
     recenz
    0.73
    лама
    0.72
    ionage
    0.71
     jednoduch
    0.70
    gants
    0.70
    </thead>
    0.69
    ateurs
    0.69
    cades
    0.68
    Activations Density 0.045%

    No Known Activations