© 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. 235200
    Prev
    Next
    INDEX
    Explanations

    must apply, music therapist, tour manager, narcotics investigators

    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
     ガ
    0.51
     提供
    0.46
    縞
    0.46
    手順
    0.45
     戦
    0.45
     a
    0.44
     黃
    0.44
    。\
    0.44
     recognisable
    0.44
     방식으로
    0.44
    POSITIVE LOGITS
     condo
    0.49
     forfeiture
    0.45
     indemn
    0.44
     йөк
    0.44
     Payton
    0.44
    Assistant
    0.43
    樘
    0.43
     dealership
    0.43
     typedef
    0.43
    ـ
    0.43
    Activations Density 0.000%

    No Known Activations