© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    tradition of

    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
    ?
    1.15
    age
    1.03
    "
    1.00
    ни
    0.98
     on
    0.96
    end
    0.92
    are
    0.88
    .
    0.88
     defunct
    0.85
    on
    0.85
    POSITIVE LOGITS
     Been
    1.17
     Αν
    1.13
     Оно
    1.06
     Ι
    1.04
     Traditions
    1.04
     Анд
    1.00
    বাহী
    1.00
    W
    1.00
    শালী
    0.99
     Иванов
    0.99
    Activations Density 0.006%

    No Known Activations