© 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. 134314
    Prev
    Next
    INDEX
    Explanations

    approaching

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

    most efficient

    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
     изображения
    0.49
     множество
    0.47
     плоско
    0.45
    𝟎
    0.42
     nop
    0.42
    ّٰ
    0.42
    וֹ
    0.42
    еха
    0.42
     numpy
    0.42
     又
    0.41
    POSITIVE LOGITS
    بانی
    0.53
    dub
    0.51
    drum
    0.50
    manage
    0.48
    druk
    0.47
    دق
    0.47
    deling
    0.46
    diesel
    0.46
    নিজ
    0.46
    dau
    0.46
    Activations Density 0.000%

    No Known Activations