© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135444
    Prev
    Next
    INDEX
    Explanations

    foreign languages and internet tasks

    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_31_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
     motorbike
    0.47
     picnics
    0.46
     ideally
    0.46
     cuddle
    0.46
    Ideally
    0.45
    🫧
    0.43
     meditation
    0.43
     squats
    0.42
     diet
    0.42
     copies
    0.42
    POSITIVE LOGITS
    ЕР
    0.49
    伙伴
    0.43
     nové
    0.43
    لمات
    0.43
    ជំងឺ
    0.42
     информа
    0.41
    抨
    0.40
     народов
    0.40
     événement
    0.40
     EVENT
    0.39
    Activations Density 0.004%

    No Known Activations