© 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. 6991
    Prev
    Next
    INDEX
    Explanations

    investigate and review

    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
     nM
    0.87
    ადი
    0.80
    थरूम
    0.79
     帽子
    0.78
    plicity
    0.78
    Wt
    0.77
    𝑠
    0.74
    ː
    0.74
     Distribution
    0.73
     gallery
    0.73
    POSITIVE LOGITS
     investigating
    1.43
     investigate
    1.37
     committee
    1.36
     committees
    1.36
     inquiry
    1.34
     tasked
    1.31
     Committee
    1.29
     investigation
    1.28
     investigations
    1.24
    Committee
    1.24
    Activations Density 0.045%

    No Known Activations