© 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. 69407
    Prev
    Next
    INDEX
    Explanations

    since Istarted to. Thejust increasing'sretire fromAs youalready livedsee ,

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

    medical statistics and diagnoses

    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
    mayan
    0.52
     ninguno
    0.50
     انھوں
    0.50
    מ
    0.50
    Pourquoi
    0.49
     മുഹമ്മ
    0.49
     solamente
    0.48
     que
    0.48
    Bran
    0.47
    PROBLEM
    0.47
    POSITIVE LOGITS
     nightclubs
    0.44
     réc
    0.43
    憬
    0.43
     screenings
    0.43
     affidavits
    0.42
    蚀
    0.41
     Organ
    0.41
     impressing
    0.40
     Tops
    0.40
     ataxia
    0.40
    Activations Density 0.001%

    No Known Activations