© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43152
    Prev
    Next
    INDEX
    Explanations

    FlashAttention

    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_262k_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
     calorías
    0.45
     menurun
    0.43
     gastron
    0.43
     カ
    0.43
     wang
    0.43
     financiar
    0.42
    ᱩ
    0.42
    Га
    0.41
    リンク
    0.40
    神経
    0.40
    POSITIVE LOGITS
     also
    0.48
    also
    0.43
     Também
    0.43
    ക്കുകയും
    0.43
     أيضا
    0.42
     Also
    0.41
    '
    0.41
     Preferably
    0.41
     ايضا
    0.40
    Determine
    0.40
    Activations Density 0.001%

    No Known Activations