© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 157735
    Prev
    Next
    INDEX
    Explanations

    unusual jobs or specific items

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

    Chinese text detection

    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_262k_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
     compagn
    0.51
    ਾਲ
    0.50
     toets
    0.49
     chauff
    0.48
    イナー
    0.48
    夥伴
    0.48
    驛
    0.47
     klingt
    0.47
     companionship
    0.46
     compagnia
    0.46
    POSITIVE LOGITS
     स्प्रे
    0.50
     Laws
    0.41
     Unusual
    0.41
    </ul>
    0.40
     असामान्य
    0.40
    抖音
    0.40
     இதுவரை
    0.40
    近年来
    0.40
    奇异
    0.39
    เค
    0.39
    Activations Density 0.002%

    No Known Activations