© 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-65K
    7. 47273
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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
    Œ
    0.48
    хам
    0.43
    zeum
    0.42
    矨
    0.42
    номер
    0.41
    ómicas
    0.41
     नोटिफिकेशन
    0.40
     чел
    0.40
    ্নান
    0.40
     मोटरसाइकिल
    0.40
    POSITIVE LOGITS
    s
    0.54
     was
    0.47
    ↵
    0.47
     TV
    0.45
     search
    0.45
     Compare
    0.44
     s
    0.44
     compare
    0.44
    Eight
    0.44
     Search
    0.43
    Activations Density 0.004%

    No Known Activations