Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6990
    Prev
    Next
    INDEX
    Explanations

    latex math alignment

    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
    ගත්
    0.48
    subheader
    0.45
    أ
    0.45
    ար
    0.43
    మాల
    0.41
    ру
    0.41
    şiktaş
    0.41
    මත්
    0.40
    radar
    0.40
    رداری
    0.40
    POSITIVE LOGITS
     적
    0.40
     上
    0.40
     とする
    0.39
    <0xF2>
    0.38
     。
    0.38
     および
    0.38
     have
    0.37
    >
    0.37
     bash
    0.37
    )
    0.37
    Activations Density 0.002%

    No Known Activations