© 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. 184226
    Prev
    Next
    INDEX
    Explanations

    blue tooth accessories

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

    breakdown of categories

    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
    receive
    0.46
    Axis
    0.44
    Each
    0.44
    Sphere
    0.44
    class
    0.43
    Observe
    0.43
    宮城県
    0.43
    礽
    0.43
    View
    0.43
    Europa
    0.43
    POSITIVE LOGITS
    وث
    0.51
     MUS
    0.45
     bảo
    0.44
     Questo
    0.44
     wskaz
    0.44
     róż
    0.43
    nání
    0.42
     questo
    0.42
    פור
    0.41
     Verfahren
    0.41
    Activations Density 0.000%

    No Known Activations