© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 903
    Prev
    Next
    INDEX
    Explanations

    printed output

    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
    ر
    3.29
    '$
    2.94
    ب
    2.88
    ato
    2.82
     IBOutlet
    2.68
     ℃
    2.67
    𝘦
    2.65
     outstanding
    2.64
     awe
    2.54
    𝘢
    2.51
    POSITIVE LOGITS
    laws
    3.35
    lived
    3.07
    ted
    2.93
    rements
    2.87
    glichen
    2.81
    la
    2.75
    lan
    2.71
    dans
    2.69
    おそらく
    2.66
    lu
    2.65
    Activations Density 0.560%

    No Known Activations