© 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. 50567
    Prev
    Next
    INDEX
    Explanations

    use carving

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

    proper nouns or specific entities

    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
    Ắ
    0.54
    ﺸ
    0.52
     ACTUAL
    0.51
    ৬৮
    0.51
     lagged
    0.49
     깜
    0.48
     lettres
    0.48
     לנו
    0.46
     চিঠি
    0.46
    ITTING
    0.44
    POSITIVE LOGITS
    ки
    0.58
    кат
    0.52
    मांड
    0.50
    кати
    0.50
    ни
    0.50
    蔑
    0.49
    వరి
    0.49
    нил
    0.48
    ’
    0.46
    тов
    0.46
    Activations Density 0.000%

    No Known Activations