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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139149
    Prev
    Next
    INDEX
    Explanations

    emotion rage culture biases

    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
    Property
    0.49
     nb
    0.49
     tiempo
    0.47
    خ
    0.47
    gg
    0.47
     for
    0.47
    ↵↵↵
    0.45
     calcul
    0.45
     tempo
    0.45
    Chris
    0.45
    POSITIVE LOGITS
     seminars
    0.49
     போக்கு
    0.46
    दरअसल
    0.45
    煸
    0.45
    ಸ್ಕೊ
    0.44
    बाइक
    0.43
    硬盘
    0.43
     முடிக்க
    0.43
    本机
    0.42
     hMut
    0.42
    Activations Density 0.000%

    No Known Activations