© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80864
    Prev
    Next
    INDEX
    Explanations

    questions about life, purpose, or relationships

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     دید
    0.48
    }$).
    0.45
     ditambah
    0.44
    ການ
    0.42
    יין
    0.41
    ปฏิบัติ
    0.41
     पूछताछ
    0.41
    ']."
    0.41
    𝔰
    0.41
    可以说是
    0.40
    POSITIVE LOGITS
     átomos
    0.53
     rota
    0.47
    cích
    0.43
     μετα
    0.42
     humanos
    0.42
     ná
    0.42
    down
    0.40
    Цент
    0.40
     Københav
    0.40
    mén
    0.40
    Activations Density 0.008%

    No Known Activations