© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    allow me, us, time

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

    allowing or permitting actions

    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
     apologized
    0.76
    ي
    0.70
     apologize
    0.68
     amelyet
    0.67
     أ
    0.67
    s
    0.67
    높
    0.65
    ש
    0.65
     amikor
    0.64
    وأ
    0.64
    POSITIVE LOGITS
    allows
    0.92
     permitirá
    0.90
     дозво
    0.88
    ALLOW
    0.87
     ALLOW
    0.84
     permite
    0.84
     позволяет
    0.84
     позволяют
    0.82
     permette
    0.82
     permitió
    0.82
    Activations Density 0.068%

    No Known Activations