© 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. 248181
    Prev
    Next
    INDEX
    Explanations

    memorial committee

    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
     appartient
    0.49
    ୍କ
    0.44
     প্রসিদ্ধ
    0.44
     Entonces
    0.43
    Điều
    0.43
    Mua
    0.43
    我
    0.43
    Ș
    0.43
     ktorá
    0.42
    ক্তি
    0.42
    POSITIVE LOGITS
    are
    0.62
    he
    0.57
    the
    0.52
    has
    0.52
    hern
    0.52
    were
    0.51
    erv
    0.51
     الگ
    0.50
    har
    0.50
    uch
    0.49
    Activations Density 0.000%

    No Known Activations