© 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-16K
    7. 73
    Prev
    Next
    INDEX
    Explanations

    new object instantiation

    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_16k_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
    ان
    0.96
    3
    0.93
    6
    0.90
     poked
    0.88
     Roblox
    0.85
    ل
    0.85
    8
    0.84
    7
    0.84
    5
    0.84
    4
    0.83
    POSITIVE LOGITS
    絠
    0.80
    𝙴
    0.69
    urgy
    0.65
     doskona
    0.63
    िनी
    0.62
    สัน
    0.62
     callSettings
    0.61
    ⅾ
    0.61
    ൂ
    0.61
    ہ
    0.61
    Activations Density 0.366%

    No Known Activations