© 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. 191637
    Prev
    Next
    INDEX
    Explanations

    started with, for as, since one

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

    draining

    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
     Berikut
    0.53
     Q
    0.47
     H
    0.47
     folgende
    0.47
     Bản
    0.46
     Fake
    0.46
    crime
    0.46
     Laura
    0.46
     ...
    0.46
     W
    0.46
    POSITIVE LOGITS
    蚩
    0.50
    視野
    0.46
    менту
    0.45
     препара
    0.44
    اسو
    0.44
     douceur
    0.44
    比較的
    0.44
    झाने
    0.44
    ႃႇ
    0.44
    摺
    0.44
    Activations Density 0.000%

    No Known Activations