© 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. 41981
    Prev
    Next
    INDEX
    Explanations

    large scale applications

    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
     on
    0.85
    า
    0.84
    ен
    0.82
    st
    0.81
    aan
    0.75
    stid
    0.75
    traits
    0.72
    ah
    0.71
    ла
    0.71
    man
    0.70
    POSITIVE LOGITS
     scale
    1.13
    Scale
    1.09
     dort
    0.95
    Кто
    0.91
    ي
    0.88
    スケ
    0.87
    尺度
    0.86
     epoca
    0.86
    其他
    0.85
    ח
    0.85
    Activations Density 0.008%

    No Known Activations