© 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. 244017
    Prev
    Next
    INDEX
    Explanations

    pronouns and descriptive nouns

    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
    2
    0.45
    聴
    0.43
    <h6>
    0.42
    izó
    0.42
    Ciao
    0.42
    sw
    0.41
    当前
    0.41
    üz
    0.40
     começou
    0.39
    ről
    0.39
    POSITIVE LOGITS
     хі
    0.51
     ફાય
    0.50
     খাজ
    0.50
     xylem
    0.49
     кукуру
    0.48
    氇
    0.47
    bottomMargin
    0.47
    стин
    0.47
     पाण्याची
    0.47
     बोर
    0.47
    Activations Density 0.000%

    No Known Activations