© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12281
    Prev
    Next
    INDEX
    Explanations

    parameters and configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Endereco
    0.92
    Características
    0.89
    鹕
    0.87
    Identification
    0.87
    Siehe
    0.85
    Bộ
    0.85
    Identify
    0.84
    Goods
    0.84
    셍
    0.83
    Generic
    0.82
    POSITIVE LOGITS
     trud
    1.09
     planting
    1.01
     inefficient
    0.98
     algorithm
    0.98
     smile
    0.98
     demoral
    0.98
     larval
    0.98
     rookie
    0.97
     amelior
    0.96
     problem
    0.96
    Activations Density 0.037%

    No Known Activations