© 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. 109661
    Prev
    Next
    INDEX
    Explanations

    following certain words

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

    production and investment

    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
    ResponseWriter
    0.49
    änz
    0.48
     nieruch
    0.48
    Wert
    0.47
     serre
    0.46
    vare
    0.46
    Raz
    0.46
    Ł
    0.45
     diffère
    0.45
     മൊ
    0.45
    POSITIVE LOGITS
    のア
    0.50
    t
    0.45
     camaraderie
    0.44
     thus
    0.42
     உண்டு
    0.42
    т
    0.42
     thereby
    0.42
     scalars
    0.42
     основы
    0.42
    ки
    0.41
    Activations Density 0.003%

    No Known Activations