© 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. 18927
    Prev
    Next
    INDEX
    Explanations

    may not use, reproduce, modify, assign, distribute

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

    can/cannot use

    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
    誘導
    0.45
    gross
    0.45
    NEUTRON
    0.44
    inductive
    0.44
    沸
    0.42
     Nathan
    0.41
     ligaments
    0.41
    傭
    0.41
     نسبت
    0.40
    йної
    0.40
    POSITIVE LOGITS
    t
    0.55
     enact
    0.43
     nutzt
    0.43
     использовать
    0.43
     accedi
    0.42
     inclui
    0.42
     tampoco
    0.41
    δας
    0.40
     bruge
    0.40
     operate
    0.40
    Activations Density 0.000%

    No Known Activations