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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3470
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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_65k_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
     laatste
    0.72
     paci
    0.71
    傚
    0.71
    zentration
    0.70
    呮
    0.70
     else
    0.69
    īgi
    0.69
    庤
    0.69
     '-':
    0.69
    濋
    0.68
    POSITIVE LOGITS
    stakes
    0.67
    lika
    0.66
    Hundreds
    0.62
    orro
    0.62
    lik
    0.61
    eresa
    0.60
     offenders
    0.58
    ed
    0.57
    Frank
    0.57
    ამდ
    0.57
    Activations Density 0.021%

    No Known Activations