© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116883
    Prev
    Next
    INDEX
    Explanations

    meteorite

    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
    り
    0.66
    ル
    0.66
    '
    0.64
    向けの
    0.63
    \
    0.63
    В
    0.62
    </h3>
    0.61
    municipal
    0.60
    ли
    0.60
    ’
    0.60
    POSITIVE LOGITS
    y
    0.82
    '):
    0.66
    ا
    0.62
    ్ఞ
    0.58
    orna
    0.56
     taj
    0.55
    amn
    0.55
     ~/.
    0.55
     daj
    0.54
    or
    0.54
    Activations Density 0.001%

    No Known Activations