© 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. 212347
    Prev
    Next
    INDEX
    Explanations

    describing actions or timeframes

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

    The Empire Strikes Back, ketoconazole, tax implications

    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
     打开
    0.54
     timpul
    0.52
     bể
    0.52
     开始
    0.51
     Vinh
    0.50
    يروس
    0.49
    硗
    0.49
     Ấ
    0.47
    akap
    0.47
    azón
    0.47
    POSITIVE LOGITS
    defined
    0.47
    exemple
    0.44
    '],
    0.43
    訂
    0.43
     localization
    0.42
     scandal
    0.42
    哀
    0.42
    럼
    0.42
    ​
    0.41
    ODA
    0.41
    Activations Density 0.000%

    No Known Activations