© 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. 116894
    Prev
    Next
    INDEX
    Explanations

    information or content

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

    explanation of subsequent actions

    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
     미술
    0.51
    FirebaseAuth
    0.49
    짜
    0.49
    getUsername
    0.47
     Стра
    0.47
    ่าง
    0.47
     ਆਪਣੇ
    0.46
    Eau
    0.46
     bầu
    0.46
     trẻ
    0.46
    POSITIVE LOGITS
    en
    0.61
     T
    0.55
     semidefinite
    0.55
    0.47
     pard
    0.46
    works
    0.46
     kvadrat
    0.46
     lineal
    0.46
     deadline
    0.46
     contains
    0.45
    Activations Density 0.001%

    No Known Activations