© 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. 128349
    Prev
    Next
    INDEX
    Explanations

    cookbook, then doing

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

    room to move

    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
     ブ
    0.44
     settlers
    0.44
     पुष्प
    0.44
     रंगों
    0.44
     legger
    0.44
     pitt
    0.43
    }$-
    0.42
     schwer
    0.41
     cw
    0.41
    )};
    0.41
    POSITIVE LOGITS
    х
    0.46
    نم
    0.45
    휼
    0.44
    enem
    0.44
    arında
    0.43
    жными
    0.43
    ถ
    0.42
    еты
    0.42
    ա
    0.42
    са
    0.42
    Activations Density 0.000%

    No Known Activations