© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14729
    Prev
    Next
    INDEX
    Explanations

    instructions, tasks, or commands

    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_262k_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
    icoter
    0.89
    腌
    0.84
    দুল
    0.83
    ক্ষিতে
    0.83
    ාවිත
    0.81
    维生素
    0.81
     indir
    0.79
    IDGE
    0.79
    ೇತ್ರ
    0.78
    舧
    0.77
    POSITIVE LOGITS
     isang
    0.76
     algo
    0.71
    gets
    0.67
     sebuah
    0.66
    baliknya
    0.66
     its
    0.66
     og
    0.66
     und
    0.65
     Shaft
    0.63
     Lane
    0.61
    Activations Density 0.000%

    No Known Activations