© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71797
    Prev
    Next
    INDEX
    Explanations

    really good

    np_acts-logits-general · gemini-2.5-flash-lite

    attic, grieve, They initiated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     costado
    0.49
    чение
    0.48
    леты
    0.45
    %$
    0.44
    ha
    0.44
     nacional
    0.42
    Payment
    0.42
    मी
    0.42
     koup
    0.42
     vaccinated
    0.41
    POSITIVE LOGITS
    鏻
    0.50
     nltk
    0.49
    钗
    0.48
    ㅢ
    0.48
    鶚
    0.46
    ાય
    0.46
    萜
    0.46
     odkry
    0.46
    ayangkan
    0.46
    wikidata
    0.43
    Activations Density 0.002%

    No Known Activations