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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7250
    Prev
    Next
    INDEX
    Explanations

    hybrid and override concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ために
    3.51
    ે
    3.28
     forefront
    2.90
    ため
    2.89
    ためには
    2.86
    es
    2.85
    isnull
    2.73
    escu
    2.73
    ാര്യ
    2.73
     inroads
    2.72
    POSITIVE LOGITS
    ع
    3.24
    に
    3.15
    д
    3.04
    ف
    2.80
    й
    2.67
    로
    2.59
     dată
    2.57
    ный
    2.55
    년을
    2.53
    atang
    2.52
    Activations Density 0.199%

    No Known Activations