© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10649
    Prev
    Next
    INDEX
    Explanations

    fill in the blank

    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_40_width_16k_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
     ойнотуу
    0.51
     живот
    0.46
    朼
    0.43
     दर्शन
    0.42
    跺
    0.42
    Emphasis
    0.41
    RANGE
    0.41
    秇
    0.40
    rements
    0.40
    丳
    0.39
    POSITIVE LOGITS
     adjective
    0.77
     adjectives
    0.67
     adj
    0.58
     gratuito
    0.54
     adjoint
    0.48
     fraudulent
    0.48
     hilly
    0.48
     faulty
    0.48
     উত্তম
    0.47
    形容
    0.47
    Activations Density 0.496%

    No Known Activations