© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
    '
    0.47
    uje
    0.42
     to
    0.39
    ate
    0.38
    -
    0.37
    ly
    0.35
    你
    0.34
    ließlich
    0.33
    ot
    0.32
    ต์
    0.31
    POSITIVE LOGITS
    ]
    0.55
    )
    0.54
    기
    0.44
    스
    0.42
    К
    0.41
    의
    0.39
    の
    0.39
    ),
    0.38
    the
    0.36
    న్
    0.35
    Activations Density 0.532%

    No Known Activations