© 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. 243398
    Prev
    Next
    INDEX
    Explanations

    genuinely born

    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
    处罚
    0.52
    球队
    0.52
     还
    0.51
     Utilisez
    0.49
     点击
    0.47
    ᕝ
    0.47
    比如说
    0.47
    壹百
    0.47
     Якщо
    0.47
    屽
    0.46
    POSITIVE LOGITS
    gen
    0.54
    ang
    0.48
    genuine
    0.47
    born
    0.45
    elia
    0.43
    ie
    0.43
     genuinely
    0.42
     genuine
    0.42
    minor
    0.42
    itare
    0.42
    Activations Density 0.000%

    No Known Activations