© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52596
    Prev
    Next
    INDEX
    Explanations

    words ending in "ational" or followed by "Identifier" or "Messenger"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يؤ
    0.44
     toată
    0.44
     islamic
    0.42
     ユ
    0.42
     पोशा
    0.42
     í
    0.41
     assuming
    0.40
     Both
    0.40
     ட
    0.40
    ーブ
    0.40
    POSITIVE LOGITS
    Cape
    0.47
    등
    0.46
    Overse
    0.45
    ob
    0.45
    གས་
    0.45
    Estr
    0.44
    Tank
    0.44
     Essen
    0.44
    Communic
    0.44
     indiqu
    0.44
    Activations Density 0.001%

    No Known Activations