© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    feature

    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
    л
    4.83
    ة
    4.30
    es
    3.75
    т
    3.63
    ת
    3.53
    ל
    3.09
    i
    3.03
    가
    2.83
    ه
    2.81
    ي
    2.79
    POSITIVE LOGITS
     prominently
    5.20
    tte
    3.37
    𝐚
    2.97
    ttes
    2.80
    parseInt
    2.74
     chast
    2.68
    ीकृत
    2.66
    𝓁
    2.60
    erings
    2.57
    fulness
    2.57
    Activations Density 0.117%

    No Known Activations