© 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. 157634
    Prev
    Next
    INDEX
    Explanations

    "had" or "has" followed by verb

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

    entities and technical terms

    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
    s
    0.48
    pé
    0.47
    *
    0.45
    wreck
    0.44
     αργ
    0.43
     и
    0.42
    е
    0.42
    IME
    0.42
     kilom
    0.42
     ను
    0.41
    POSITIVE LOGITS
    ޟ
    0.50
     creado
    0.50
    lyPlugin
    0.50
     bienvenida
    0.48
    hasFocus
    0.48
     봄
    0.47
    ندگی
    0.47
     resul
    0.47
    neſs
    0.46
    تباينه
    0.46
    Activations Density 0.000%

    No Known Activations