© 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. 33683
    Prev
    Next
    INDEX
    Explanations

    very long

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

    strict, times, service, yet

    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
    DZ
    0.55
    MAY
    0.49
     box
    0.49
    ME
    0.48
    Dz
    0.47
    흉
    0.47
     demeure
    0.47
    Ż
    0.46
    RANGER
    0.45
     zacz
    0.45
    POSITIVE LOGITS
    an
    0.49
    ற்புத
    0.47
    piro
    0.45
    ằng
    0.43
     sữa
    0.43
    សម្រ
    0.43
    newMark
    0.43
    ar
    0.42
     முன்னோ
    0.42
     세율
    0.41
    Activations Density 0.000%

    No Known Activations