© 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. 106046
    Prev
    Next
    INDEX
    Explanations

    historical, babies, injuries, results, vehicle

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

    financial, common, common tokens

    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
    ランチ
    0.46
    ladi
    0.46
    א
    0.45
    של
    0.42
    她是
    0.42
    ب
    0.42
    Exclusive
    0.42
    ப்பட்டு
    0.41
    شارك
    0.41
    نا
    0.40
    POSITIVE LOGITS
     cán
    0.49
     tỷ
    0.47
     গ্রামা
    0.47
     tục
    0.46
    queta
    0.46
    ၇
    0.46
     ಹಣ
    0.45
     tỉ
    0.45
     घरे
    0.45
     строк
    0.44
    Activations Density 0.000%

    No Known Activations