© 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. 73769
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    </em>
    -1.57
    '
    -1.26
    ↵↵
    -1.13
     häufiger
    -1.06
     something
    -1.04
    U
    -1.02
    O
    -0.99
     Produkten
    -0.99
     礼物
    -0.97
    le
    -0.97
    POSITIVE LOGITS
     that
    1.70
    tió
    1.34
    ometries
    1.32
     będ
    1.30
     wzglę
    1.27
     getApplication
    1.27
     povezave
    1.27
    –¿
    1.26
     melewati
    1.26
    Trichloroethane
    1.25
    Activations Density 0.110%

    No Known Activations