© 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. 10-GEMMASCOPE-RES-131K
    7. 9707
    Prev
    Next
    INDEX
    Explanations

    technical methods and studies

    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
    ørte
    -1.19
    viewDid
    -1.12
    ihnachts
    -1.09
     ње
    -1.06
    為了
    -1.05
    vá
    -1.02
    ꧁
    -1.02
    Trotz
    -1.02
    россий
    -1.02
    这里
    -1.02
    POSITIVE LOGITS
    www
    1.39
     these
    1.18
     These
    1.17
     very
    1.16
    ',
    1.16
     this
    1.13
     some
    1.13
    ering
    1.11
     Consequently
    1.10
     same
    1.09
    Activations Density 0.194%

    No Known Activations