© 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. 9571
    Prev
    Next
    INDEX
    Explanations

    extra addition or supplement

    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
    ल
    1.25
    یم
    1.11
    )
    1.11
    ک
    1.06
    $
    1.01
    cı
    0.99
     moistur
    0.98
    ],”
    0.98
    وی
    0.94
    ]
    0.94
    POSITIVE LOGITS
     Extra
    1.05
    man
    0.97
     extra
    0.97
    extra
    0.95
    z
    0.84
    㶲
    0.84
    𝙜
    0.83
     on
    0.82
    Extra
    0.82
     为了
    0.82
    Activations Density 0.004%

    No Known Activations