© 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. 29331
    Prev
    Next
    INDEX
    Explanations

    for reasons or durations

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

    includes also

    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
    ↵↵
    0.52
     faulted
    0.48
    NavigationView
    0.41
    PictureBox
    0.40
     spectacularly
    0.40
     crafted
    0.40
     నుంచి
    0.40
     وړاند
    0.39
    брав
    0.39
    ﻨ
    0.39
    POSITIVE LOGITS
    í
    0.58
    මෙ
    0.57
    he
    0.54
    are
    0.54
     he
    0.51
    ale
    0.51
    they
    0.49
    ik
    0.48
     unele
    0.47
    that
    0.47
    Activations Density 0.290%

    No Known Activations