© 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. 62445
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related contexts

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

    or, Definition, similar

    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
     runs
    0.50
     records
    0.49
     scores
    0.49
     pints
    0.49
    Q
    0.48
     endpoints
    0.47
     milestones
    0.47
    See
    0.46
     statistics
    0.45
    ↵
    0.44
    POSITIVE LOGITS
    reten
    0.52
     garantizar
    0.50
    umlu
    0.48
    قات
    0.47
     Masyarakat
    0.47
     Harus
    0.47
     চুক্তি
    0.46
    تبار
    0.46
    tpVar
    0.46
    ogad
    0.46
    Activations Density 0.001%

    No Known Activations