© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221216
    Prev
    Next
    INDEX
    Explanations

    identifying nouns or descriptions

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

    "poly" or foreign language equivalents

    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
    Negative Logits
    登录
    0.52
    c
    0.51
     inches
    0.50
    ین
    0.49
    ак
    0.48
    r
    0.48
    ين
    0.47
    ريض
    0.46
    它
    0.46
    O
    0.46
    POSITIVE LOGITS
     вигляді
    0.50
     הולנד
    0.49
     tossing
    0.47
    knings
    0.45
     impuls
    0.45
     사람은
    0.45
    );}
    0.45
     polyd
    0.45
     이동
    0.45
     дітей
    0.44
    Activations Density 0.001%

    No Known Activations