© 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. 84039
    Prev
    Next
    INDEX
    Explanations

    when conditions are met

    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
     privacidad
    0.45
    REZ
    0.43
     fix
    0.42
     camin
    0.42
    mlabeledtr
    0.42
    秙
    0.42
     trialComponents
    0.41
     movilidad
    0.41
     swapping
    0.41
     ໜອງ
    0.41
    POSITIVE LOGITS
    When
    0.51
     When
    0.47
     علیکم
    0.45
    देश
    0.42
    რ
    0.42
    میں
    0.41
    젊
    0.41
    ニュー
    0.41
     Budapest
    0.40
    Germany
    0.40
    Activations Density 0.007%

    No Known Activations