© 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. 13521
    Prev
    Next
    INDEX
    Explanations

    However, early, report back

    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
     CHROM
    1.27
     żeby
    1.22
    Კ
    1.21
    ТИ
    1.21
    ‍♀
    1.21
    ᅪ
    1.18
    ぜひ
    1.17
    ες
    1.17
     присоеди
    1.17
    僚
    1.17
    POSITIVE LOGITS
    Tanh
    0.89
    bower
    0.87
    ある
    0.85
    ceptar
    0.83
     handful
    0.81
     exemplary
    0.79
    mathrm
    0.76
    ק
    0.75
     semblance
    0.75
    extrait
    0.74
    Activations Density 0.001%

    No Known Activations