© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15704
    Prev
    Next
    INDEX
    Explanations

    reason for harmful intent

    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_65k_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
     山
    0.48
    ताप
    0.47
     ⏮
    0.45
     አይነት
    0.43
     如何
    0.41
     పుస్త
    0.40
    ले
    0.40
    लामा
    0.40
    뉩
    0.40
    ⵚ
    0.39
    POSITIVE LOGITS
     sheer
    0.58
     vanwege
    0.49
     karena
    0.49
    因为它
    0.47
    出于
    0.46
     porque
    0.46
     because
    0.46
     względu
    0.46
    乐趣
    0.44
     purely
    0.44
    Activations Density 0.066%

    No Known Activations