© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13688
    Prev
    Next
    INDEX
    Explanations

    geopolitical conflict and public opinion

    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_17_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
    pson
    0.79
    Ḵ
    0.76
    াব্দ
    0.75
     clothing
    0.75
    five
    0.75
     Banyak
    0.75
    ails
    0.75
     gynec
    0.73
    a
    0.72
     other
    0.71
    POSITIVE LOGITS
    会不会
    0.84
     গোলাবার
    0.83
     magma
    0.83
    ₴
    0.82
    Volatility
    0.81
     безпе
    0.81
     bekom
    0.80
     scary
    0.80
     sapere
    0.80
     volatil
    0.80
    Activations Density 0.049%

    No Known Activations