© 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-16K
    7. 13191
    Prev
    Next
    INDEX
    Explanations

    positive feedback and satisfaction

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

    possessive pronouns across languages

    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_16k_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
    私は
    0.50
    コ
    0.49
    我自己
    0.46
     絶対
    0.46
     sq
    0.45
    隸
    0.42
    ೩
    0.41
    単
    0.41
     ロー
    0.40
    openia
    0.40
    POSITIVE LOGITS
     unserer
    0.62
     naszych
    0.61
     naš
    0.59
     naszego
    0.59
     unseres
    0.58
     satisfacción
    0.58
     our
    0.57
     нашей
    0.55
     हमारी
    0.55
     наших
    0.54
    Activations Density 0.115%

    No Known Activations