© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 497
    Prev
    Next
    INDEX
    Explanations

    fake and pretend scenarios

    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_40_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
    ITÉ
    0.36
     STYLE
    0.34
     гото
    0.33
     Directly
    0.33
     Ş
    0.33
    ཿ
    0.33
    ただ
    0.32
     underrated
    0.32
     directly
    0.32
     TAM
    0.32
    POSITIVE LOGITS
     fake
    0.94
    假的
    0.90
    假
    0.87
     Fake
    0.82
     faux
    0.81
    Fake
    0.80
     pretend
    0.79
     pretends
    0.79
    fake
    0.77
     pretending
    0.77
    Activations Density 0.055%

    No Known Activations