© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14454
    Prev
    Next
    INDEX
    Explanations

    adversarial attacks and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ب
    1.30
    ا
    1.26
    و
    1.16
    مت
    1.14
    다
    1.12
    お
    1.12
    ला
    1.02
    ना
    1.01
    ‌ها
    1.00
    ”
    0.97
    POSITIVE LOGITS
    s
    1.41
    n
    1.39
    z
    1.30
    w
    1.21
    p
    1.09
    b
    1.06
    r
    1.02
    with
    0.96
    v
    0.86
    t
    0.85
    Activations Density 0.004%

    No Known Activations