© 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. 22-GEMMASCOPE-RES-131K
    7. 73896
    Prev
    Next
    INDEX
    Explanations

    keys in structured data

    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
    bague
    -1.09
    事が
    -1.08
    之事
    -1.06
    Kapcsolódó
    -1.05
    outheast
    -1.05
    yyb
    -1.05
     Weisheit
    -1.04
    insee
    -1.02
     stratég
    -1.02
     három
    -1.02
    POSITIVE LOGITS
    这让
    1.14
    甦
    1.10
    Siapa
    1.10
    Kenapa
    1.07
    Impressum
    1.06
     only
    1.04
    は
    1.01
    Еще
    1.00
    Publicado
    1.00
     also
    1.00
    Activations Density 0.010%

    No Known Activations