© 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. 155159
    Prev
    Next
    INDEX
    Explanations

    student, examination, protest, discussion

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

    offering explore open

    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
    现在
    0.50
    馏
    0.44
    筛选
    0.44
    的人生
    0.44
    üllen
    0.43
     prevented
    0.43
    纽约
    0.43
    ავს
    0.43
    Return
    0.42
    ounces
    0.42
    POSITIVE LOGITS
     طالب
    0.52
     चर्चे
    0.50
     സമര
    0.49
     ф
    0.48
     mahasiswa
    0.48
     फ
    0.47
     Gandh
    0.46
     დაკ
    0.46
     zah
    0.46
     Examination
    0.43
    Activations Density 0.000%

    No Known Activations