© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3164
    Prev
    Next
    INDEX
    Explanations

    multilingual queries and code

    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_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
     രീതി
    0.55
     అనేది
    0.52
     ভাবে
    0.44
     విషయంలో
    0.42
     목록
    0.42
    を利用
    0.42
    ů
    0.42
     પ્રકાર
    0.41
     때문에
    0.41
    ようで
    0.41
    POSITIVE LOGITS
    a
    0.60
     നിന്ന്
    0.54
    ad
    0.54
     alınan
    0.50
    行った
    0.48
     இருந்து
    0.47
    进行的
    0.47
     있던
    0.46
    ab
    0.44
    iz
    0.43
    Activations Density 0.018%

    No Known Activations