© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    C++ cout statements

    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
    д
    1.53
     asunto
    1.50
    ़
    1.41
    ટ
    1.31
    ്
    1.29
    ில்
    1.27
    اری
    1.24
    也就是说
    1.22
    ী
    1.22
    <bos>
    1.22
    POSITIVE LOGITS
    هُ
    1.38
    𝗰
    1.34
    𝐫
    1.30
    𝐥
    1.27
     AnyObject
    1.26
    oader
    1.25
    𝗁
    1.25
    ه
    1.22
    ्स
    1.20
    തിരെ
    1.19
    Activations Density 0.052%

    No Known Activations