© 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. 5900
    Prev
    Next
    INDEX
    Explanations

    arrangements and structures

    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
     verschill
    0.70
     Indian
    0.66
     याची
    0.62
     older
    0.62
     Choibalsan
    0.62
    ଼
    0.60
     indian
    0.60
     neighbouring
    0.60
     increments
    0.60
    तीन
    0.59
    POSITIVE LOGITS
     delightfully
    0.83
    یس
    0.83
     delicioso
    0.82
     Rave
    0.81
     امیدوار
    0.80
     крайне
    0.79
     sabiduría
    0.78
    Э
    0.77
     надеюсь
    0.77
    政治
    0.77
    Activations Density 0.233%

    No Known Activations