© 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. 18171
    Prev
    Next
    INDEX
    Explanations

    IM Well

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

    data analysis and constants

    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
     devotes
    0.50
    ロ
    0.50
     устро
    0.47
     нейтра
    0.47
     पार्
    0.45
    шие
    0.45
    quela
    0.45
     \{\
    0.44
    丈
    0.44
    idencia
    0.44
    POSITIVE LOGITS
     Healy
    0.46
     Myrtle
    0.46
     Vale
    0.44
    沍
    0.42
    Vale
    0.42
    埴
    0.41
     Transparency
    0.41
     ترلاسه
    0.40
     Peace
    0.39
     ক্ষীণ
    0.39
    Activations Density 0.001%

    No Known Activations