© 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. 8556
    Prev
    Next
    INDEX
    Explanations

    ACLs, lumps, salt, bitrate

    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
    ت
    1.73
    نيا
    1.65
    [
    1.53
    س
    1.49
    स
    1.48
    ような
    1.46
    ์
    1.45
    ש
    1.43
    ie
    1.38
    ৬
    1.37
    POSITIVE LOGITS
    𝓵
    1.70
    𝓼
    1.69
    ದ್ದರಿಂದ
    1.62
     garçon
    1.61
    нансо
    1.61
    𝓻
    1.54
    tenance
    1.52
     julg
    1.51
     refrain
    1.50
    𝓷
    1.42
    Activations Density 0.000%

    No Known Activations