© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    resources for further reading

    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
     Toxicity
    0.84
     Golpe
    0.81
     duelo
    0.81
     enticing
    0.80
    ым
    0.78
    ка
    0.76
    ➩
    0.75
     Thrive
    0.75
     élő
    0.75
     Translational
    0.75
    POSITIVE LOGITS
     всем
    0.67
    ↵↵
    0.64
     init
    0.62
     सहित
    0.62
    ini
    0.62
     όλ
    0.61
     ما
    0.61
    Init
    0.60
     dua
    0.59
    |\
    0.59
    Activations Density 0.002%

    No Known Activations