© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210731
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and rates

    np_acts-logits-general · gemini-2.5-flash-lite

    literal vs figurative meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wafer
    0.50
     thực
    0.44
     flange
    0.44
     तिच्या
    0.44
     i
    0.44
     ii
    0.44
     răng
    0.43
     caustic
    0.43
    entukan
    0.43
    ASTIC
    0.43
    POSITIVE LOGITS
    راك
    0.54
    verlag
    0.53
    一覧
    0.51
    廨
    0.47
    شكال
    0.47
    λέ
    0.47
    ということで
    0.46
    펩
    0.46
    ပါ
    0.46
    кей
    0.46
    Activations Density 0.001%

    No Known Activations