© 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. 67473
    Prev
    Next
    INDEX
    Explanations

    data processing

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

    possessive pronouns and attribution

    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
    1
    0.53
    riven
    0.50
    رام
    0.48
    נ
    0.45
    /
    0.45
    نز
    0.44
    kan
    0.43
    但也
    0.43
    زه
    0.42
    min
    0.42
    POSITIVE LOGITS
     hänen
    0.59
     ње
    0.56
     그의
    0.50
     Managing
    0.49
     usefulness
    0.49
     showering
    0.48
     သူ့
    0.48
     옵
    0.47
    ："
    0.46
     microprocessor
    0.46
    Activations Density 0.001%

    No Known Activations