© 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. 56002
    Prev
    Next
    INDEX
    Explanations

    descriptions of states and characteristics

    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
     equivalents
    0.48
    Camb
    0.47
     undue
    0.46
     counterparts
    0.44
     primers
    0.44
     you
    0.44
    ূন্য
    0.44
     negroes
    0.43
    name
    0.42
    定
    0.42
    POSITIVE LOGITS
     ແລະ
    0.42
     आणि
    0.41
     Macbook
    0.41
     Samsung
    0.40
     odby
    0.40
     कॉम्प
    0.40
    <0xE2>
    0.40
     અને
    0.40
     büyük
    0.40
     বিক্ষোভ
    0.39
    Activations Density 0.014%

    No Known Activations