© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4086
    Prev
    Next
    INDEX
    Explanations

    women's rights, sensuality, outfit, perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     
    1.73
    те
    1.67
     mocy
    1.56
    ка
    1.54
    го
    1.52
    。
    1.52
    서
    1.51
     어
    1.49
     불구하고
    1.48
    ته
    1.43
    POSITIVE LOGITS
    ifiably
    2.22
    lardan
    2.14
    ması
    1.96
    lular
    1.94
    y
    1.93
    iflor
    1.86
    larda
    1.83
    lendi
    1.79
    luit
    1.79
    lığı
    1.77
    Activations Density 0.005%

    No Known Activations