© 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. 249250
    Prev
    Next
    INDEX
    Explanations

    medical residency, bilingual facilitator, replica watches, full length

    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
    হইল
    0.54
    となった
    0.49
    BLACKLIST
    0.49
     остаются
    0.48
    短い
    0.48
    صیٰ
    0.47
     atta
    0.47
    ﺠ
    0.47
    ृति
    0.46
     verwij
    0.46
    POSITIVE LOGITS
     Zuh
    0.46
    ouncer
    0.46
    iod
    0.44
     matem
    0.44
     Dome
    0.44
    ikan
    0.44
    jem
    0.44
    ķ
    0.44
     Sanderson
    0.43
    math
    0.43
    Activations Density 0.000%

    No Known Activations