© 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. 62428
    Prev
    Next
    INDEX
    Explanations

    quantities and sequences

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

    estar or to be

    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
    isées
    0.48
     Canon
    0.46
    }=\
    0.45
    ús
    0.45
     Šk
    0.44
     Bloch
    0.43
     Cycles
    0.43
     steelhead
    0.43
    на
    0.43
    ୀ
    0.43
    POSITIVE LOGITS
     เรียน
    0.52
    📒
    0.46
     uds
    0.44
    割り
    0.44
     learn
    0.44
     complacent
    0.44
     ไม่
    0.44
    ักษ
    0.43
     lear
    0.43
     รับ
    0.43
    Activations Density 0.000%

    No Known Activations