© 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. 16-GEMMASCOPE-2-RES-262K
    4. 41304
    Prev
    Next
    INDEX
    Explanations

    temptation and being tempted

    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_16_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
    يل
    0.91
    洺
    0.84
    				
    0.80
    ště
    0.74
    ță
    0.74
    țin
    0.72
    りと
    0.71
     sexu
    0.69
    ného
    0.68
    <0x80>
    0.68
    POSITIVE LOGITS
    ↵↵
    1.42
    u
    1.12
     Tempt
    1.00
    e
    1.00
     temptations
    0.98
     temptation
    0.98
    d
    0.97
    don
    0.96
    i
    0.95
    a
    0.94
    Activations Density 0.001%

    No Known Activations