© 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. 95329
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    introduces elaboration or continuation

    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
     результа
    0.46
    зина
    0.42
    遭受
    0.42
    ፌ
    0.41
    ле
    0.40
     неодно
    0.39
    ल्पनिक
    0.39
    дови
    0.39
    ಾನೂ
    0.38
    круг
    0.38
    POSITIVE LOGITS
     以下
    0.47
     执行
    0.47
    Pyrimidine
    0.44
     控制
    0.44
     甲
    0.44
     yuè
    0.44
     ندير
    0.43
    ,,
    0.42
     ascent
    0.39
    ，
    0.39
    Activations Density 0.000%

    No Known Activations