© 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. 116723
    Prev
    Next
    INDEX
    Explanations

    incomemaintaining spouse

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

    relatable and humor

    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
     looting
    0.49
     impatience
    0.46
    pricing
    0.45
     evasion
    0.45
    maturity
    0.45
    invasion
    0.44
     intolerable
    0.43
    ル
    0.43
    shooting
    0.42
    funding
    0.42
    POSITIVE LOGITS
     Чар
    0.49
    حل
    0.48
    してみてください
    0.46
    这是一个
    0.46
    им
    0.44
    ь
    0.43
    Ӏо
    0.43
    они
    0.42
     definir
    0.42
     костю
    0.42
    Activations Density 0.001%

    No Known Activations