© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4506
    Prev
    Next
    INDEX
    Explanations

    Strong AI

    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
    Negative Logits
     Спорт
    0.43
    高度
    0.40
    dürü
    0.40
     ආකාර
    0.39
    nmid
    0.39
     Hälfte
    0.38
    ='\
    0.38
    rification
    0.37
    park
    0.37
    ष्कार
    0.37
    POSITIVE LOGITS
     strong
    1.77
     stronger
    1.70
     Strong
    1.68
    Strong
    1.64
     kuat
    1.61
    強
    1.59
     मजबूत
    1.58
     STRONG
    1.58
    strong
    1.56
     fuertes
    1.52
    Activations Density 0.203%

    No Known Activations