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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6398
    Prev
    Next
    INDEX
    Explanations

    aforementioned [challenges, issues, payoff, paradigm, gut, aircraft, example, regulatory]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    es
    1.38
    an
    1.36
    as
    1.28
    ंना
    1.16
    os
    1.15
     aank
    1.07
    ী
    1.07
    ский
    1.05
    ных
    1.05
     homot
    1.05
    POSITIVE LOGITS
    ্যালেঞ্জ
    1.23
     supposing
    1.13
    I
    1.02
     sufferings
    0.98
    orsement
    0.97
    لی
    0.95
    ר
    0.95
    侄
    0.95
     ดิ
    0.94
    لد
    0.92
    Activations Density 0.000%

    No Known Activations