© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    evaluating processes and functions

    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
    ແລະ
    1.20
    และ
    1.17
     एवं
    1.16
     और
    1.09
     आणि
    1.08
     и
    1.08
     និង
    1.08
    和
    1.05
     및
    1.05
     மற்றும்
    1.04
    POSITIVE LOGITS
     consisting
    1.24
     consists
    1.15
     namely
    1.13
    namely
    1.11
    ەکە
    1.10
     特に
    1.04
     firstly
    1.02
    အနေ
    1.00
     eftersom
    0.98
     deoarece
    0.97
    Activations Density 0.168%

    No Known Activations