© 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. 40-GEMMASCOPE-2-RES-65K
    7. 4034
    Prev
    Next
    INDEX
    Explanations

    for clarity

    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_40_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
    in
    0.32
    ed
    0.27
    V
    0.26
     При
    0.26
    เพื่อ
    0.25
     presence
    0.25
    ing
    0.25
     Example
    0.25
     по
    0.24
     Sliver
    0.24
    POSITIVE LOGITS
    kfollowers
    0.27
     bagaimana
    0.25
    ссии
    0.24
    क्ती
    0.24
    ॉर्क
    0.24
    UNICATIONS
    0.23
    ޔ
    0.23
     kuidas
    0.23
     cómo
    0.23
    بود
    0.23
    Activations Density 0.210%

    No Known Activations