© 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. 135119
    Prev
    Next
    INDEX
    Explanations

    disaster, risk, and ethical concepts

    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
    acruz
    0.41
    olytic
    0.39
    asibility
    0.38
    sthe
    0.38
    AWS
    0.38
    winged
    0.37
    idence
    0.37
     양
    0.36
    structured
    0.36
     primordial
    0.36
    POSITIVE LOGITS
     Reno
    0.52
     zwięks
    0.50
     extérieures
    0.49
     Profit
    0.48
     théorie
    0.48
     Projet
    0.47
     răm
    0.46
     tăng
    0.46
     Isaiah
    0.46
     进行
    0.46
    Activations Density 0.001%

    No Known Activations