© 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. 8313
    Prev
    Next
    INDEX
    Explanations

    digits and separators

    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
    муля
    2.39
     recyclerView
    2.34
    htmlspecialchars
    2.30
    Mere
    2.25
     useState
    2.24
    ﻲ
    2.22
    𝘻
    2.18
    bookmark
    2.17
    们的
    2.15
    inputText
    2.13
    POSITIVE LOGITS
     Palash
    2.77
     mamy
    2.67
     perkara
    2.67
     прямо
    2.65
     cuid
    2.44
    Else
    2.44
    '}).
    2.42
    ্লিশ
    2.41
     tributes
    2.39
     Undoubtedly
    2.37
    Activations Density 0.080%

    No Known Activations