© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13145
    Prev
    Next
    INDEX
    Explanations

    coding identifiers

    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
     csak
    -1.40
     cualquier
    -1.22
    CELONA
    -1.21
    amaño
    -1.21
    举动
    -1.20
    ܣ
    -1.20
    Opel
    -1.20
     enige
    -1.20
    utdown
    -1.19
    Energie
    -1.18
    POSITIVE LOGITS
     which
    1.70
     on
    1.48
     that
    1.35
     Accordingly
    1.28
    ou
    1.28
     würden
    1.28
     Polícia
    1.19
     evtl
    1.14
     You
    1.13
     Plenty
    1.13
    Activations Density 0.020%

    No Known Activations