© 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. 174499
    Prev
    Next
    INDEX
    Explanations

    possessive and subsequent nouns

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

    explaining properties or conditions

    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
     Martyrs
    0.48
    ကြား
    0.48
     médicas
    0.46
    ينات
    0.45
     hemodynamic
    0.45
    𒊩
    0.45
     Sunlight
    0.44
     Movement
    0.44
     فوج
    0.44
     Elytres
    0.44
    POSITIVE LOGITS
    zero
    0.54
    pivot
    0.50
    written
    0.49
    parallel
    0.47
    cesa
    0.47
    app
    0.46
    you
    0.46
    attaque
    0.46
    设
    0.45
    et
    0.45
    Activations Density 0.000%

    No Known Activations