© 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. 12935
    Prev
    Next
    INDEX
    Explanations

    say:say:say:

    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
    Volt
    0.71
    ΜΑ
    0.71
    睄
    0.70
     applaud
    0.69
    Қ
    0.68
    事項
    0.66
    ので
    0.66
    Treasurer
    0.66
     applauded
    0.65
    ቬ
    0.64
    POSITIVE LOGITS
    a
    0.82
    i
    0.80
    sized
    0.72
    s
    0.72
    nic
    0.65
    impl
    0.64
    e
    0.60
    daten
    0.60
    atility
    0.60
    minecraft
    0.59
    Activations Density 0.000%

    No Known Activations