© 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. 196192
    Prev
    Next
    INDEX
    Explanations

    exploring their

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

    control

    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
    ні
    0.55
    ו
    0.48
    ਾ
    0.46
    te
    0.45
    Di
    0.45
    K
    0.45
    τέ
    0.44
    <0xBE>
    0.44
    4
    0.44
    Union
    0.44
    POSITIVE LOGITS
     ویژگی
    0.51
    敒
    0.47
    annels
    0.46
    图片
    0.46
     参数
    0.46
     விதைகள்
    0.46
    舴
    0.46
     রাক
    0.45
     గారి
    0.45
    뭅
    0.45
    Activations Density 0.001%

    No Known Activations