© 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. 6638
    Prev
    Next
    INDEX
    Explanations

    experimental research design

    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
    of
    1.15
    '
    0.95
     can
    0.93
    ння
    0.88
    اسی
    0.88
    า
    0.88
    க்
    0.86
    కు
    0.86
    است
    0.85
    וס
    0.84
    POSITIVE LOGITS
    r
    0.84
    z
    0.82
    ell
    0.78
    pl
    0.75
     ein
    0.74
    x
    0.74
    其他
    0.73
    ec
    0.73
    没有什么
    0.72
    ام
    0.71
    Activations Density 0.006%

    No Known Activations