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. 7271
    Prev
    Next
    INDEX
    Explanations

    left side of body

    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
    𝗥
    1.34
    𝗸
    1.30
    𝗲
    1.30
    𝗜
    1.24
    𝗶
    1.23
     निकले
    1.20
    𝗚
    1.20
    𝗘
    1.17
     inconsistencies
    1.17
     annan
    1.14
    POSITIVE LOGITS
    ន៍
    1.44
     preach
    1.33
    ័យ
    1.33
    不管
    1.32
     hablamos
    1.32
     rid
    1.29
    yya
    1.26
     elevating
    1.25
     civiles
    1.25
    ેશન
    1.24
    Activations Density 0.000%

    No Known Activations