© 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. 28929
    Prev
    Next
    INDEX
    Explanations

    adding new elements

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

    adding context or continuing sequences

    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
    ruc
    0.40
     మర
    0.40
    ruč
    0.39
    rote
    0.38
    ಾನೆ
    0.38
     организм
    0.38
    ं
    0.38
     テ
    0.38
    ंचा
    0.38
    炳
    0.37
    POSITIVE LOGITS
     proactively
    0.48
     kèm
    0.45
     jeśli
    0.44
     proactive
    0.44
     egalitarian
    0.43
     添加
    0.43
    を追加
    0.43
     pós
    0.43
     interrelated
    0.42
     ardından
    0.41
    Activations Density 0.000%

    No Known Activations