© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    average of, your time

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

    priorities, categories, or options

    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
     součást
    0.46
    kách
    0.46
    保湿
    0.45
     nguyên
    0.44
    đi
    0.44
    ၻ
    0.44
    nému
    0.43
    מל
    0.43
    攵
    0.43
    ваясь
    0.42
    POSITIVE LOGITS
     Priorities
    0.47
    eit
    0.43
     दोन्ही
    0.43
    有两个
    0.42
     categories
    0.41
     priorities
    0.41
     juggle
    0.41
    PerPage
    0.40
    Patterns
    0.40
    ).—
    0.38
    Activations Density 0.000%

    No Known Activations