© 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. 183446
    Prev
    Next
    INDEX
    Explanations

    bearings and price

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

    breakingresultformerTakes inAnything

    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
    場
    0.51
    ulle
    0.46
    んに
    0.45
    érables
    0.44
    uality
    0.44
    ToOne
    0.44
    вары
    0.44
    %，
    0.44
    ㌔
    0.43
     studies
    0.42
    POSITIVE LOGITS
     mı
    0.54
    谚
    0.52
    苍
    0.47
     забезпечення
    0.47
     ochron
    0.46
     saepe
    0.43
     সীমান্ত
    0.43
     katıl
    0.43
    되지
    0.43
     सर्किट
    0.43
    Activations Density 0.000%

    No Known Activations