© 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. 22-GEMMASCOPE-RES-131K
    7. 130404
    Prev
    Next
    INDEX
    Explanations

    questions about specific measures

    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
     Amazing
    -1.20
     people
    -1.19
     its
    -1.16
     Ministero
    -1.07
     various
    -1.07
     However
    -1.07
     beserta
    -1.06
     hennes
    -1.05
     with
    -1.02
    著名的
    -1.02
    POSITIVE LOGITS
    preferably
    1.34
     acepción
    1.22
     corr
    1.16
    熜
    1.13
     exportación
    1.13
     sám
    1.12
     trám
    1.11
     sostenibilidad
    1.11
    wants
    1.10
    weren
    1.10
    Activations Density 0.065%

    No Known Activations