© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    features and values

    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
    <0x80>
    1.72
    ים
    1.65
    ੀ
    1.65
    т
    1.43
    িং
    1.40
    ０
    1.33
    できる
    1.32
    𝘨
    1.30
    یی
    1.27
    ت
    1.27
    POSITIVE LOGITS
     I
    1.66
     potenti
    1.36
    و
    1.34
    ض
    1.29
     enorm
    1.26
    .
    1.25
     be
    1.23
    其他
    1.16
    w
    1.13
    رة
    1.12
    Activations Density 0.057%

    No Known Activations