© 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. 12540
    Prev
    Next
    INDEX
    Explanations

    among others, among the

    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
    िक
    3.31
    𝙖
    2.51
    چ
    2.32
    𝙣
    2.28
    في
    2.24
     daraus
    2.19
     manera
    2.17
    𝙩
    2.16
    க்கு
    2.12
    ating
    2.04
    POSITIVE LOGITS
    ר
    3.07
    st
    3.01
    et
    2.92
    ت
    2.90
    d
    2.88
    народ
    2.86
    maßen
    2.78
    tanto
    2.69
    зем
    2.67
     andet
    2.64
    Activations Density 0.020%

    No Known Activations