© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    past participles then nouns

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

    past-tense participles

    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
    ﺸ
    0.79
     İlk
    0.78
     équip
    0.75
     término
    0.74
     तत्कालीन
    0.73
    amending
    0.72
     Đà
    0.72
     î
    0.71
     académico
    0.70
     Mün
    0.70
    POSITIVE LOGITS
    ت
    1.85
    س
    1.40
    त
    1.27
    و
    1.24
    т
    1.20
    י
    1.20
    ל
    1.20
    с
    1.17
    i
    1.08
    et
    1.07
    Activations Density 0.557%

    No Known Activations