© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    degree symbol

    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
    nables
    -1.11
    XXXXXX
    -1.03
    ,-.
    -1.02
    ɵɵelementEnd
    -1.00
    dled
    -1.00
    <[
    -0.98
    拚
    -0.98
     them
    -0.98
    \_\_
    -0.97
    ically
    -0.96
    POSITIVE LOGITS
     Bereichen
    0.96
    érat
    0.96
     issuing
    0.95
    Bö
    0.95
    دانشنامهٔ
    0.94
    tempuran
    0.93
     спросил
    0.93
    Almost
    0.93
    lectricité
    0.91
     flèche
    0.90
    Activations Density 0.008%

    No Known Activations