© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35981
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
     therefore
    -1.33
     например
    -1.17
     Therefore
    -1.16
     Thus
    -1.16
    Therefore
    -1.14
     thus
    -1.10
     وزار
    -1.07
    eg
    -1.05
    Thus
    -1.04
    therefore
    -1.00
    POSITIVE LOGITS
     still
    1.70
    still
    1.13
     ocultar
    1.11
    +};
    1.06
     guapa
    1.05
     always
    1.03
     fortfarande
    1.02
     patří
    1.02
     note
    1.00
     empêcher
    0.97
    Activations Density 0.033%

    No Known Activations