© 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. 106825
    Prev
    Next
    INDEX
    Explanations

    medication pills

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

    disable wireless communication

    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
     Use
    0.50
     Thousands
    0.50
     Serious
    0.50
    I
    0.49
     Inhib
    0.48
    D
    0.48
     रिएक्शन
    0.48
     Milk
    0.48
    Milk
    0.48
     Reach
    0.48
    POSITIVE LOGITS
     inscrib
    0.54
    diendo
    0.53
     multiplicar
    0.53
    φ
    0.52
     chamar
    0.52
     apportion
    0.50
     asignar
    0.50
     φ
    0.49
     relacion
    0.49
     aclarar
    0.48
    Activations Density 0.000%

    No Known Activations