© 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. 48724
    Prev
    Next
    INDEX
    Explanations

    fine-tuning, occupied, specific wavelengths

    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
     достижения
    0.44
     ブ
    0.43
     incar
    0.42
    ure
    0.41
    opian
    0.41
    fier
    0.41
    determ
    0.40
    onos
    0.40
    ron
    0.40
     عق
    0.40
    POSITIVE LOGITS
     čty
    0.58
     навіть
    0.53
     negativo
    0.48
     četiri
    0.47
    ölt
    0.47
    詿
    0.47
     bốn
    0.46
     čtyř
    0.46
     eigene
    0.46
     völl
    0.46
    Activations Density 0.002%

    No Known Activations