© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101847
    Prev
    Next
    INDEX
    Explanations

    not included, should not

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

    off-grid communication, options, uncertainty

    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
    áról
    0.48
     епи
    0.46
     సౌ
    0.45
     начальник
    0.44
    LocalStorage
    0.44
    硒
    0.44
    储存
    0.43
    鋰
    0.43
     निलंबित
    0.43
    濃度
    0.43
    POSITIVE LOGITS
     girl
    0.59
     Girl
    0.55
     Sindh
    0.50
     Mahindra
    0.50
     Sid
    0.49
     Brandy
    0.49
    ف
    0.49
     trusses
    0.48
     Trish
    0.47
     Sidd
    0.46
    Activations Density 0.000%

    No Known Activations