© 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. 104245
    Prev
    Next
    INDEX
    Explanations

    names of organizations

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

    text examples or definitions

    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
     inn
    0.46
    葢
    0.44
    浥
    0.42
     elm
    0.41
     म्हट
    0.41
     خوف
    0.41
    менить
    0.41
    䣫
    0.41
     جهت
    0.40
    Hound
    0.40
    POSITIVE LOGITS
    ↵↵
    0.71
    ↵↵↵
    0.57
    ↵↵↵↵
    0.46
    વ
    0.45
    ijev
    0.45
    า
    0.42
    ch
    0.42
    čí
    0.42
    д
    0.41
    <start_of_image>
    0.41
    Activations Density 0.036%

    No Known Activations