© 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. 36699
    Prev
    Next
    INDEX
    Explanations

    This software, lots of, little known

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

    playfully mischievous or creative explanations

    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
     عندهم
    0.47
    动的
    0.43
     Marco
    0.43
     من
    0.42
     -
    0.42
    uan
    0.42
    ﻮ
    0.41
    ô
    0.40
     থাকেন
    0.40
     who
    0.39
    POSITIVE LOGITS
    対策
    0.54
    AndroidResource
    0.48
     interno
    0.47
     файла
    0.46
    曳
    0.46
    щую
    0.45
     wewnętr
    0.45
     fogy
    0.45
     limitaciones
    0.45
    accessibility
    0.44
    Activations Density 0.000%

    No Known Activations