© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9726
    Prev
    Next
    INDEX
    Explanations

    logarithmic complexity, financial trade-offs, efficient calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elders
    0.52
    ins
    0.48
    ’
    0.48
    <h2>
    0.46
     elders
    0.45
    eld
    0.43
     Context
    0.43
     Surge
    0.43
     Erickson
    0.42
    Context
    0.42
    POSITIVE LOGITS
     เส
    0.51
     протяжении
    0.45
     LOTRAchievement
    0.44
     увеличение
    0.44
     terecht
    0.44
     ı
    0.43
     pasaj
    0.43
     разви
    0.42
     Расійскай
    0.42
    λογή
    0.41
    Activations Density 0.013%

    No Known Activations