© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66895
    Prev
    Next
    INDEX
    Explanations

    see how or that

    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
    钜
    -1.52
     time
    -1.41
     Some
    -1.40
     Using
    -1.34
     selben
    -1.30
     understand
    -1.30
     When
    -1.29
     sürü
    -1.27
     Every
    -1.27
     becomes
    -1.27
    POSITIVE LOGITS
    盉
    1.69
    甃
    1.54
    '
    1.45
    鲧
    1.41
     totalmente
    1.41
     -'
    1.38
     Tt
    1.38
     ſever
    1.34
     bolig
    1.33
     Chrif
    1.32
    Activations Density 0.056%

    No Known Activations