© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 137572
    Prev
    Next
    INDEX
    Explanations

    definitions and categories

    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_16_width_262k_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
    ៈ
    0.59
    кона
    0.55
     學
    0.52
     vaisse
    0.51
    जबकि
    0.51
    祜
    0.51
    ificio
    0.51
     ለእ
    0.51
    ಕ್ಕಾಗಿ
    0.50
     dakkh
    0.50
    POSITIVE LOGITS
     as
    0.70
    _
    0.52
     by
    0.52
     girls
    0.51
     pound
    0.51
    t
    0.51
    ล
    0.49
     and
    0.48
     who
    0.48
     rå
    0.48
    Activations Density 0.000%

    No Known Activations