© 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. 119677
    Prev
    Next
    INDEX
    Explanations

    when do

    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
     in
    -1.37
     почина
    -1.22
     egentlig
    -1.16
    ctomy
    -1.09
    illeen
    -1.07
    ši
    -1.06
    imantan
    -1.05
     vanskelig
    -1.05
     aldri
    -1.04
    "%(
    -1.04
    POSITIVE LOGITS
     freaking
    1.22
     "
    1.14
     said
    1.13
    みなさん
    1.13
    Quando
    1.12
     repeti
    1.11
    ของคุณ
    1.09
    [\
    1.07
    หรือ
    1.06
     freakin
    1.05
    Activations Density 0.202%

    No Known Activations