© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22507
    Prev
    Next
    INDEX
    Explanations

    So,

    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
     I
    0.51
     لد
    0.48
     Simulations
    0.47
     V
    0.47
    ivorous
    0.46
     bushing
    0.45
     spirals
    0.44
    ساعدة
    0.43
     depreciation
    0.42
     Satisfaction
    0.42
    POSITIVE LOGITS
    した
    0.90
    ،
    0.74
    _
    0.70
    、
    0.69
    ，
    0.66
    ၊
    0.65
    歴史
    0.64
    った
    0.62
    ła
    0.59
    なぜ
    0.59
    Activations Density 0.015%

    No Known Activations