© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1004
    Prev
    Next
    INDEX
    Explanations

    the [diverse nouns]

    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
    一个
    2.29
    з
    1.79
     frente
    1.71
    ஸ்
    1.67
     implode
    1.65
    However
    1.63
    Ironically
    1.60
    Founded
    1.57
     edhe
    1.53
    스
    1.53
    POSITIVE LOGITS
     especially
    2.00
    蔼
    1.98
    rews
    1.97
    ंगाबाद
    1.94
    rogens
    1.93
     seterusnya
    1.92
     others
    1.81
     hatta
    1.79
    especially
    1.77
     zwar
    1.72
    Activations Density 0.080%

    No Known Activations