© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    assurance of support

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

    Chinese, Romanian, natural, country

    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_16k_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
    de
    0.52
    hed
    0.50
    nice
    0.48
    GIN
    0.47
    signer
    0.46
    Shr
    0.46
    ނ
    0.44
    wart
    0.44
     Susanne
    0.44
    And
    0.44
    POSITIVE LOGITS
     kiz
    0.52
     prodotti
    0.49
    ૌ
    0.47
     Disse
    0.46
    峈
    0.46
     crois
    0.46
    ოლოდ
    0.45
     വ്യത്യസ്ത
    0.44
     сфе
    0.44
     Ansatz
    0.44
    Activations Density 0.003%

    No Known Activations