© 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. 33861
    Prev
    Next
    INDEX
    Explanations

    describing "some" cases

    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
     délais
    -1.63
    isn
    -1.42
     inconvénients
    -1.34
     conejo
    -1.30
     célè
    -1.30
     savent
    -1.30
     cóc
    -1.28
     dépenses
    -1.27
     échanti
    -1.27
    久し
    -1.25
    POSITIVE LOGITS
     just
    1.79
     to
    1.73
     simply
    1.59
     merely
    1.42
     with
    1.35
     only
    1.34
     только
    1.26
     more
    1.24
     различные
    1.23
     do
    1.21
    Activations Density 0.039%

    No Known Activations