© 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. 150971
    Prev
    Next
    INDEX
    Explanations

    information about methods and results

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

    preparing or preprocessing before

    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
    𝖺
    0.53
    紹介
    0.52
    า
    0.52
    та
    0.51
    א
    0.50
    ɑ
    0.50
    ू
    0.48
    ણ
    0.48
    ઋ
    0.47
     넓
    0.47
    POSITIVE LOGITS
    方法的
    0.45
     digging
    0.44
     treating
    0.43
     crawling
    0.42
    drinking
    0.42
     browsing
    0.42
     this
    0.42
     paying
    0.41
    args
    0.41
    results
    0.41
    Activations Density 0.001%

    No Known Activations