© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2289
    Prev
    Next
    INDEX
    Explanations

    clicking buttons or links

    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
    ی
    3.83
    י
    3.75
    بك
    3.37
    க்கு
    3.23
    ្ល
    2.98
    ный
    2.98
    potentially
    2.97
    i
    2.96
    ⟹
    2.82
    𝙈
    2.81
    POSITIVE LOGITS
    س
    3.64
    ारण
    3.52
    берите
    3.41
     heels
    3.33
    こと
    3.27
    ্ব
    3.22
    ה
    3.21
    եր
    2.92
    েও
    2.92
    heid
    2.92
    Activations Density 0.301%

    No Known Activations