© 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. 10-GEMMASCOPE-RES-131K
    7. 42841
    Prev
    Next
    INDEX
    Explanations

    in some places/patients/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_10/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
     and
    -1.53
     after
    -1.44
     should
    -1.41
    jelaskan
    -1.28
     båda
    -1.27
    cocina
    -1.20
     після
    -1.19
     at
    -1.19
     most
    -1.18
     After
    -1.17
    POSITIVE LOGITS
     incluso
    1.70
     incluyendo
    1.61
    甚至
    1.53
     sogar
    1.52
    ori
    1.43
    whelmed
    1.38
    "
    1.34
    ……"
    1.31
    da
    1.30
     alors
    1.30
    Activations Density 0.130%

    No Known Activations