© 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. 70372
    Prev
    Next
    INDEX
    Explanations

    Local union affiliations

    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
     about
    -1.48
     but
    -1.26
    P
    -1.20
    ないけど
    -1.18
     vendu
    -1.18
    FIGURE
    -1.13
     diseñar
    -1.10
    L
    -1.10
    Q
    -1.09
     ícones
    -1.09
    POSITIVE LOGITS
    ksessa
    1.28
    chuckles
    1.25
    Vra
    1.21
    llä
    1.16
     olarak
    1.16
    ativen
    1.15
    ttä
    1.15
    zą
    1.15
    lique
    1.14
    Cevap
    1.14
    Activations Density 0.020%

    No Known Activations