Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 90
    Prev
    Next
    INDEX
    Explanations

    charged defendants

    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_16_width_16k_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
    et
    0.49
     Handling
    0.49
    er
    0.47
    del
    0.47
    ar
    0.46
    STER
    0.46
    P
    0.46
     Dealing
    0.46
    ik
    0.45
    there
    0.44
    POSITIVE LOGITS
    頴
    0.54
     鳥
    0.54
     estern
    0.54
     francês
    0.54
     próp
    0.52
    iseen
    0.52
     なさい
    0.52
     quanta
    0.52
     letteratura
    0.52
     முன்னே
    0.51
    Activations Density 0.000%

    No Known Activations