© 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. 72026
    Prev
    Next
    INDEX
    Explanations

    limited offer

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

    expected situation

    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
    荫
    0.46
    勋
    0.45
    aner
    0.45
     glEnable
    0.44
    inum
    0.43
    ianie
    0.43
    音
    0.42
    邹
    0.42
    格納
    0.42
    ioides
    0.42
    POSITIVE LOGITS
     placenta
    0.46
     партия
    0.46
     കണ
    0.44
     ट्विटर
    0.43
    पोर्ट
    0.42
     பிரி
    0.42
     Plac
    0.42
    কেট
    0.42
     forhold
    0.42
     ἢ
    0.42
    Activations Density 0.007%

    No Known Activations