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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9260
    Prev
    Next
    INDEX
    Explanations

    location is constantly shifting

    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_22_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
    ]%
    0.76
    oksatta
    0.73
     Численность
    0.72
     резидент
    0.72
    স্তে
    0.71
     convoc
    0.69
     cps
    0.67
    VICE
    0.66
     SIR
    0.66
    pipelines
    0.66
    POSITIVE LOGITS
     taught
    0.63
    taught
    0.61
    押
    0.61
    ০০০
    0.59
     শিখ
    0.58
    とも
    0.58
     pelas
    0.57
    हरू
    0.57
    िलाई
    0.57
     Processor
    0.57
    Activations Density 0.000%

    No Known Activations