© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3225
    Prev
    Next
    INDEX
    Explanations

    then followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    0
    1.88
    t
    1.77
    5
    1.50
    ing
    1.49
    {
    1.39
    <0x80>
    1.38
    1
    1.38
    he
    1.36
    8
    1.35
    er
    1.34
    POSITIVE LOGITS
    ल
    1.72
    на
    1.55
    ל
    1.40
    ก
    1.39
    ل
    1.29
    나
    1.25
    مس
    1.23
    น
    1.20
    л
    1.19
    기
    1.19
    Activations Density 0.141%

    No Known Activations