© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159854
    Prev
    Next
    INDEX
    Explanations

    consumer friendly deity

    np_acts-logits-general · gemini-2.5-flash-lite

    strict safety guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    気に入り
    0.51
     YoY
    0.47
     Insert
    0.47
    缃
    0.46
     ezzel
    0.44
     イエロー
    0.44
     SwitchCompat
    0.43
    烬
    0.43
    çamento
    0.42
     oficialmente
    0.42
    POSITIVE LOGITS
    Legisl
    0.49
    Schemas
    0.47
    Nature
    0.46
     그리스
    0.46
    Sal
    0.46
    Hughes
    0.46
    Bene
    0.46
    Μ
    0.46
    Patients
    0.46
    Biological
    0.46
    Activations Density 0.000%

    No Known Activations