© 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. 238228
    Prev
    Next
    INDEX
    Explanations

    no injuries, stitching, speed, reports, design

    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
    嬗
    0.52
    гре
    0.51
    ين
    0.48
    ५
    0.47
    するために
    0.47
    ವಿದೆ
    0.47
    ತ್ರಿ
    0.47
    ⿹
    0.46
    データ
    0.46
     ڈیٹا
    0.46
    POSITIVE LOGITS
    owner
    0.52
     whore
    0.51
     pim
    0.48
     买
    0.48
    when
    0.48
     p
    0.47
     vs
    0.47
     when
    0.46
     銀
    0.46
     王
    0.45
    Activations Density 0.000%

    No Known Activations