© 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. 109596
    Prev
    Next
    INDEX
    Explanations

    writing creative content

    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
     Acquisitions
    0.52
    τας
    0.47
     Hil
    0.47
    Hil
    0.47
    adis
    0.46
     afectada
    0.46
    ται
    0.46
    屾
    0.46
     consumidores
    0.43
    stüt
    0.42
    POSITIVE LOGITS
    ～。
    0.51
     оконча
    0.48
     його
    0.46
    alabel
    0.46
     démar
    0.46
     شكل
    0.46
     ફો
    0.45
     جناب
    0.43
     criminal
    0.43
    ні
    0.43
    Activations Density 0.000%

    No Known Activations