© 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. 69823
    Prev
    Next
    INDEX
    Explanations

    people's names or project 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
     ataupun
    -1.34
    ächlich
    -1.31
     اختلال
    -1.28
     احتم
    -1.20
     tij
    -1.20
    簌
    -1.20
    väl
    -1.18
    ,«
    -1.17
     resultat
    -1.17
    taj
    -1.17
    POSITIVE LOGITS
     would
    1.67
     its
    1.49
     it
    1.47
     again
    1.30
     each
    1.17
     didn
    1.16
    它的
    1.15
     give
    1.14
    一言
    1.13
     act
    1.10
    Activations Density 0.049%

    No Known Activations