© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23092
    Prev
    Next
    INDEX
    Explanations

    too good to be true

    np_acts-logits-general · gemini-2.5-flash-lite

    unrealistic promises and schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    影响
    0.47
    擾
    0.44
    ົດ
    0.43
     distressing
    0.42
     지원
    0.41
    影響
    0.41
     wrongly
    0.41
    扰
    0.41
     afectadas
    0.41
     evidencias
    0.40
    POSITIVE LOGITS
     suspiciously
    0.71
     suspicious
    0.70
     tempting
    0.56
    誘
    0.51
     tempt
    0.50
     temptation
    0.49
     Tempt
    0.47
     слишком
    0.47
     temptations
    0.47
     terlalu
    0.46
    Activations Density 0.041%

    No Known Activations