© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3334
    Prev
    Next
    INDEX
    Explanations

    as of today, november 2, 2023

    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_29_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
    杪
    0.69
     КС
    0.66
     initiated
    0.64
     nay
    0.64
    vora
    0.64
    ーブ
    0.64
     ';
    0.64
     arranges
    0.64
     derived
    0.63
     philos
    0.63
    POSITIVE LOGITS
     ቀን
    1.08
    th
    0.76
    st
    0.76
    रेगा
    0.70
     corte
    0.69
    日に
    0.69
    тики
    0.69
    코
    0.68
    日英
    0.68
    reaction
    0.66
    Activations Density 0.071%

    No Known Activations