© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21365
    Prev
    Next
    INDEX
    Explanations

    never followed by auxiliary verbs

    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
    ⧠
    -2.63
    粜
    -2.20
     dando
    -2.20
     двумя
    -2.16
    eight
    -2.13
    ఽ
    -2.13
     eerste
    -2.02
     két
    -2.00
    VERY
    -1.95
    蓠
    -1.94
    POSITIVE LOGITS
    le
    2.36
     Since
    1.97
     have
    1.94
    In
    1.89
     Obviously
    1.88
     Interestingly
    1.88
    𓆜
    1.80
     when
    1.77
     Although
    1.76
     During
    1.76
    Activations Density 0.006%

    No Known Activations