© 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. 59058
    Prev
    Next
    INDEX
    Explanations

    accommodation and faith

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

    train leaves Chicago

    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
    ্যাক
    0.44
    Topbar
    0.44
     başladı
    0.43
    出来了
    0.43
     videolar
    0.43
    MsgCallBack
    0.42
    Clipboard
    0.42
    넹
    0.42
     основном
    0.41
     recientemente
    0.41
    POSITIVE LOGITS
     QTL
    0.51
     Equally
    0.51
    綃
    0.49
    各有
    0.44
     জ্ঞানের
    0.42
     Scandinavia
    0.42
    explo
    0.40
     TUN
    0.40
    蘊
    0.40
     equally
    0.40
    Activations Density 0.000%

    No Known Activations