© 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. 162860
    Prev
    Next
    INDEX
    Explanations

    Xbox Scorpio

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

    medical, professional roles

    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
     وسي
    0.46
     múlti
    0.46
    的
    0.46
     forfait
    0.44
    偕
    0.44
    의
    0.43
     لأ
    0.43
    쿄
    0.43
    ATIVES
    0.42
    པ
    0.42
    POSITIVE LOGITS
    IRONMENT
    0.47
     Эн
    0.47
     Harrington
    0.47
     helfen
    0.44
     आढळ
    0.43
     बंदी
    0.43
    軛
    0.43
     obsahuje
    0.43
    浬
    0.43
     zet
    0.43
    Activations Density 0.000%

    No Known Activations