© 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. 74703
    Prev
    Next
    INDEX
    Explanations

    following a specific term

    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
     bookcases
    0.46
    viruses
    0.46
    ረጋ
    0.45
    asts
    0.43
    burning
    0.41
    ሱን
    0.40
    Threads
    0.40
    U
    0.40
    Sockets
    0.39
    Ung
    0.39
    POSITIVE LOGITS
    وا
    0.58
     membro
    0.57
    ס
    0.56
     membre
    0.55
     sépar
    0.55
     miembro
    0.55
     veio
    0.54
     faith
    0.54
     aloj
    0.54
    ные
    0.53
    Activations Density 0.000%

    No Known Activations