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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47253
    Prev
    Next
    INDEX
    Explanations

    Algorithm, iteration, performing, subsequent, reported

    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_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
    :
    1.11
    že
    0.97
    )
    0.95
    :")
    0.93
    /
    0.92
    ixer
    0.91
    ≳
    0.89
    istor
    0.89
    ichever
    0.88
    ­
    0.87
    POSITIVE LOGITS
     unexpectedly
    1.14
     mitigated
    1.05
    ዜ
    1.00
    仅仅
    0.99
    treme
    0.99
    但是
    0.98
     kmeans
    0.95
     Threatened
    0.95
    ব্যাপ
    0.94
     Apparently
    0.93
    Activations Density 0.001%

    No Known Activations