© 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. 22-GEMMASCOPE-RES-131K
    7. 129039
    Prev
    Next
    INDEX
    Explanations

    programming actions or setup

    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_22/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
     capucha
    -1.58
     verschillende
    -1.53
    aning
    -1.52
     colgante
    -1.51
     calcetines
    -1.44
     cordón
    -1.44
     těchto
    -1.39
    aneity
    -1.35
     testamento
    -1.34
    嬸
    -1.34
    POSITIVE LOGITS
     even
    2.05
     from
    1.81
     just
    1.71
     only
    1.61
     if
    1.59
     for
    1.41
    Even
    1.38
     can
    1.35
    just
    1.34
     because
    1.34
    Activations Density 0.010%

    No Known Activations