© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64271
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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_65k_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
     of
    0.48
     drove
    0.46
     skipper
    0.46
     with
    0.44
     wharf
    0.44
    而
    0.42
     housewife
    0.41
     a
    0.40
    িলম্বে
    0.40
     телефо
    0.40
    POSITIVE LOGITS
     পদ্ধতি
    0.48
    دو
    0.45
    ದಾರ
    0.45
    مو
    0.44
    ر
    0.44
    ட
    0.42
    пти
    0.42
    સિંહ
    0.42
    negl
    0.42
    諄
    0.42
    Activations Density 0.004%

    No Known Activations