© 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. 28197
    Prev
    Next
    INDEX
    Explanations

    entity followed by title or descriptor

    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
    多肉
    -1.63
    綃
    -1.51
    ꯳
    -1.46
     inglês
    -1.44
    wickshire
    -1.41
    Continua
    -1.39
     aeroporto
    -1.38
     verba
    -1.38
     solida
    -1.37
     garant
    -1.36
    POSITIVE LOGITS
    :
    1.80
     theses
    1.52
    頃の
    1.51
    _
    1.47
     :
    1.45
    L
    1.36
    ;
    1.36
     можно
    1.35
     bereits
    1.34
    K
    1.32
    Activations Density 0.210%

    No Known Activations