© 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. 55699
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    definitions, descriptions, or specific terms

    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
    Initial
    0.45
    Grow
    0.44
     Seasons
    0.43
     printf
    0.42
    Queens
    0.42
    Produces
    0.42
    Sends
    0.42
    닿
    0.41
    Scorch
    0.41
    Discover
    0.41
    POSITIVE LOGITS
     ხელისუფლების
    0.59
     அளவுக்கு
    0.53
     definitively
    0.53
    策
    0.52
     பதவி
    0.51
     حکومت
    0.48
     часа
    0.48
     administrador
    0.48
     режима
    0.48
     offended
    0.47
    Activations Density 0.000%

    No Known Activations