© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50935
    Prev
    Next
    INDEX
    Explanations

    do not accept

    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_31_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
     கடும்
    0.44
    nyj
    0.44
    ГО
    0.44
    Sensitive
    0.42
    ﾅ
    0.42
    提名
    0.42
     свободы
    0.41
    Govern
    0.41
    篾
    0.41
    auch
    0.41
    POSITIVE LOGITS
     bạn
    0.69
     you
    0.60
     fácilmente
    0.58
     você
    0.58
     puedes
    0.57
     softwares
    0.57
     మీరు
    0.57
     apps
    0.54
     আপনি
    0.54
     beginners
    0.54
    Activations Density 0.005%

    No Known Activations