© 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. 95531
    Prev
    Next
    INDEX
    Explanations

    logo tag

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

    explains meaning

    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
     wouldn
    0.48
     سند
    0.46
     seep
    0.46
    ➘
    0.46
     ous
    0.45
     oss
    0.44
     needn
    0.44
     hasn
    0.44
     caseload
    0.44
    ⢸
    0.44
    POSITIVE LOGITS
    ка
    0.59
    ки
    0.50
     G
    0.48
    рик
    0.45
     T
    0.45
    ud
    0.45
    uni
    0.44
    च
    0.44
    ती
    0.43
    чика
    0.42
    Activations Density 0.001%

    No Known Activations