© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 9648
    Prev
    Next
    INDEX
    Explanations

    Δ followed by quantity

    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
     in
    1.27
    ite
    1.23
    ни
    1.17
    ט
    1.13
     an
    1.11
    </h2>
    1.06
    ون
    1.06
    </u>
    1.05
    v
    1.05
    ,
    1.02
    POSITIVE LOGITS
    。
    1.29
    ності
    1.09
     Çok
    1.05
    好
    1.02
    resolved
    0.98
    tól
    0.97
     Faça
    0.96
     Comunic
    0.96
     Hesap
    0.96
    OL
    0.95
    Activations Density 0.015%

    No Known Activations