© 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. 126244
    Prev
    Next
    INDEX
    Explanations

    killing, harming, punishable

    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
    ク
    0.50
    特
    0.49
    ч
    0.47
    編
    0.46
    ти
    0.46
    帶
    0.44
    ᅧ
    0.44
    Р
    0.44
    ब
    0.43
    加
    0.43
    POSITIVE LOGITS
     امیدوار
    0.63
     hopes
    0.47
     надеюсь
    0.47
     שא
    0.46
     southeastern
    0.46
     philanthrop
    0.46
             
    0.46
     corroborate
    0.45
     امید
    0.45
     रिजल्ट
    0.44
    Activations Density 0.004%

    No Known Activations