© 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. 157000
    Prev
    Next
    INDEX
    Explanations

    course woulddriving,washed anddsDNasecompliance is

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

    common context following words

    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
     morceau
    0.51
    爱好
    0.51
     Deep
    0.48
    챗
    0.47
     membuat
    0.47
     Shallow
    0.46
    开源
    0.45
    游戏
    0.44
     فارسی
    0.44
    模样
    0.44
    POSITIVE LOGITS
     distribu
    0.52
     preclinical
    0.49
     differentiated
    0.49
     vitro
    0.48
    🆕
    0.48
     automatically
    0.48
     =
    0.47
    ＝
    0.47
     circulatory
    0.46
     configura
    0.46
    Activations Density 0.001%

    No Known Activations