© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    leans into

    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
     l
    0.72
     n
    0.63
    <0x80>
    0.57
     B
    0.56
     h
    0.53
     II
    0.50
     каче
    0.49
     M
    0.49
    accharide
    0.49
    ’)
    0.48
    POSITIVE LOGITS
    ב
    0.79
    ة
    0.72
    ם
    0.71
    </strong>
    0.67
    3
    0.66
    </h3>
    0.65
    ヨ
    0.65
    נו
    0.64
    ద
    0.64
    ۔
    0.64
    Activations Density 0.059%

    No Known Activations