© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    user login profile

    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
    غ
    0.60
    ﺍ
    0.58
    ۔
    0.56
    は
    0.54
    מ
    0.54
    ان
    0.54
    シ
    0.54
    ك
    0.52
    ه
    0.51
    では
    0.50
    POSITIVE LOGITS
    <0x80>
    0.69
     افراد
    0.54
    oro
    0.51
     THE
    0.47
     playful
    0.46
    0.46
    amu
    0.44
    flexible
    0.44
    rek
    0.43
    ینڈ
    0.43
    Activations Density 0.206%

    No Known Activations