© 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. 31-GEMMASCOPE-2-RES-262K
    4. 12794
    Prev
    Next
    INDEX
    Explanations

    describing typical characteristics

    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_31_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
    </h3>
    0.82
    <0x0D>
    0.74
    </h1>
    0.70
     enhancing
    0.68
    </h2>
    0.68
     l
    0.66
    </h4>
    0.64
     as
    0.60
    </a>
    0.60
     redundant
    0.60
    POSITIVE LOGITS
    지만
    0.73
    ਰ
    0.66
    า
    0.66
    first
    0.62
    가
    0.61
    ра
    0.60
    이
    0.59
    рсә
    0.58
    를
    0.58
    계
    0.58
    Activations Density 0.073%

    No Known Activations