© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2783
    Prev
    Next
    INDEX
    Explanations

    end of phrase/list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ];//
    0.41
     सिम
    0.35
     sog
    0.34
     rispett
    0.33
     recentemente
    0.33
     determinadas
    0.31
     précédemment
    0.31
     recientemente
    0.30
     Cag
    0.30
     yem
    0.30
    POSITIVE LOGITS
    amsmath
    0.36
     хотят
    0.32
     Hempstead
    0.30
    둴
    0.30
     misspelled
    0.29
    sentence
    0.29
    어도
    0.29
    opee
    0.29
    െന്ന്
    0.29
    blah
    0.29
    Activations Density 0.334%

    No Known Activations