© 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. 122001
    Prev
    Next
    INDEX
    Explanations

    local applications

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

    medical regulated HIPAA

    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
    寐
    0.46
     апре
    0.46
     conceptually
    0.44
     tentative
    0.43
     TIL
    0.43
    呼び
    0.42
     AVEN
    0.42
    ະຍ
    0.42
    இந்த
    0.42
     EVIDENCE
    0.42
    POSITIVE LOGITS
     risol
    0.49
    rockets
    0.49
    
    0.47
     disque
    0.47
    knock
    0.47
     chemical
    0.46
    mén
    0.46
    ні
    0.46
     químicos
    0.45
    ził
    0.44
    Activations Density 0.002%

    No Known Activations