© 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. 31910
    Prev
    Next
    INDEX
    Explanations

    causes / conditions / descriptions

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

    code and programming concepts

    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
    詳しくは
    0.54
    如果你
    0.51
    ἱ
    0.49
    你要
    0.48
    ご了承
    0.47
     فشاں
    0.47
    茆
    0.47
    ᵚ
    0.46
    綪
    0.46
     તમે
    0.46
    POSITIVE LOGITS
     on
    0.56
    im
    0.54
    ka
    0.53
    wo
    0.51
    7
    0.50
    yl
    0.49
    ign
    0.47
    ffect
    0.47
    ipes
    0.47
    que
    0.46
    Activations Density 0.000%

    No Known Activations