© 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. 27725
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific names

    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
     three
    -1.43
    英國
    -1.21
    作家
    -1.16
     some
    -1.11
     diable
    -1.09
     several
    -1.07
    がありません
    -1.05
     two
    -1.05
     five
    -1.03
    getClassName
    -1.03
    POSITIVE LOGITS
     will
    1.25
    為に
    1.13
     to
    1.07
     jornalista
    1.02
    是以
    1.02
     např
    1.01
     fofo
    1.01
    is
    0.97
     velho
    0.97
    腴
    0.96
    Activations Density 0.004%

    No Known Activations