© 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. 249196
    Prev
    Next
    INDEX
    Explanations

    limits and 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
     নাট
    0.45
     Làm
    0.43
     Puppy
    0.42
     Colchester
    0.42
    Pupp
    0.42
    Gut
    0.41
     క్
    0.41
     [](
    0.40
     Cơ
    0.40
     مخطط
    0.40
    POSITIVE LOGITS
     propria
    0.54
     atrocities
    0.51
     renal
    0.49
     peculiarities
    0.49
    绚
    0.48
     aperta
    0.48
     eti
    0.48
     зла
    0.47
     antal
    0.47
     venga
    0.47
    Activations Density 0.000%

    No Known Activations