© 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. 170118
    Prev
    Next
    INDEX
    Explanations

    adjectives and related phrases

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

    primary identifier

    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
    偏差
    0.48
     infractions
    0.48
    値
    0.45
    =(
    0.44
     inflection
    0.44
     incident
    0.44
    不定
    0.44
    1
    0.43
    脂肪
    0.43
    HashMap
    0.43
    POSITIVE LOGITS
     doğal
    0.53
     outfitted
    0.52
     کوردستان
    0.50
     arac
    0.50
     orta
    0.48
     dağı
    0.48
     이름을
    0.48
    ladi
    0.47
     دید
    0.47
     സാ
    0.47
    Activations Density 0.000%

    No Known Activations