© 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. 6874
    Prev
    Next
    INDEX
    Explanations

    Results, Conclusion, Objective, Findings

    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
     inferred
    0.95
     them
    0.87
     monotonicity
    0.86
     |_{
    0.85
    жан
    0.83
     sufficiently
    0.82
    setPointSize
    0.82
    :\
    0.82
    0.81
    grit
    0.81
    POSITIVE LOGITS
     trabaj
    1.19
     이미
    1.09
     разговари
    1.08
     νέα
    1.06
     trader
    1.06
     Plans
    1.05
    交易
    1.05
     Talks
    1.03
     civiles
    1.03
     останов
    1.02
    Activations Density 0.007%

    No Known Activations