© 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. 202504
    Prev
    Next
    INDEX
    Explanations

    giving or receiving 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
     ليك
    0.46
     احتيا
    0.42
    適
    0.42
    autor
    0.42
     pleases
    0.42
     يك
    0.41
    ការពារ
    0.41
     requires
    0.41
     guarding
    0.41
    ievable
    0.41
    POSITIVE LOGITS
    რ
    0.51
    یمی
    0.47
     डिप्लोमा
    0.43
     EMEA
    0.43
    ᵕ
    0.43
    িকারী
    0.42
     Rae
    0.42
    飫
    0.42
     Dipl
    0.42
     Taxonomy
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.