© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66545
    Prev
    Next
    INDEX
    Explanations

    call or contact us

    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
    ってない
    -1.46
    important
    -1.30
     palco
    -1.13
     quadrinhos
    -1.13
    erdings
    -1.12
     CONTINUE
    -1.11
    が無い
    -1.10
     Schweden
    -1.09
     PLACES
    -1.09
    mainly
    -1.08
    POSITIVE LOGITS
     our
    1.86
     your
    1.78
     we
    1.60
     or
    1.54
     contact
    1.52
     you
    1.49
     давайте
    1.41
     any
    1.37
     email
    1.18
     compresión
    1.17
    Activations Density 0.035%

    No Known Activations