© 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. 75085
    Prev
    Next
    INDEX
    Explanations

    final state

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

    slipped, ducked

    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
    Lors
    0.50
    Selon
    0.50
     indústria
    0.50
     combinação
    0.48
     aplica
    0.48
    帳
    0.47
     irmãos
    0.47
     ポイント
    0.47
    もし
    0.47
     পরিক্ষ
    0.47
    POSITIVE LOGITS
     abgeschlossen
    0.46
    腆
    0.43
    entered
    0.42
    互动
    0.42
    adır
    0.42
    让我
    0.42
    铁路
    0.42
    隐藏
    0.41
     السؤال
    0.40
    隐含
    0.40
    Activations Density 0.002%

    No Known Activations