© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    li, OMI, MSI, mani, FI, ani, mi

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects proper nouns, brand/model names and technical identifiers—capitalized tokens, acronyms, and product/model-like strings.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     for
    1.66
    for
    1.63
    ن
    1.38
    st
    1.35
    T
    1.34
    ah
    1.33
    el
    1.30
    n
    1.29
    se
    1.24
    d
    1.21
    POSITIVE LOGITS
    ي
    1.79
    1
    1.47
    ی
    1.41
    i
    1.37
    u
    1.37
    ہ
    1.26
    ١
    1.26
    த்தில்
    1.25
    ி
    1.23
    ে
    1.23
    Activations Density 0.422%

    No Known Activations