© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1667
    Prev
    Next
    INDEX
    Explanations

    things that

    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_9_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
    𝖽
    1.68
    𝗌
    1.51
    тріш
    1.47
    to
    1.44
    𝗋
    1.42
    у
    1.41
    nya
    1.40
    Ꮙ
    1.39
     вр
    1.38
    imidazole
    1.35
    POSITIVE LOGITS
    an
    2.45
    er
    1.88
    べき
    1.87
    ০
    1.80
    न
    1.79
    هههه
    1.77
    aik
    1.75
    erst
    1.73
    e
    1.73
    ił
    1.71
    Activations Density 0.121%

    No Known Activations