© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10253
    Prev
    Next
    INDEX
    Explanations

    deception, knowledge, or 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
    甪
    0.49
     jut
    0.44
     สามารถ
    0.43
     effortless
    0.42
    дру
    0.41
    ExposureTime
    0.41
    కుడు
    0.41
    ﹟
    0.41
     harnessing
    0.41
     உதவும்
    0.40
    POSITIVE LOGITS
     knew
    0.67
     fraud
    0.49
     sabía
    0.49
     had
    0.48
     знали
    0.47
     hatte
    0.45
     oedd
    0.44
     questioned
    0.44
     знал
    0.44
     buvo
    0.43
    Activations Density 0.049%

    No Known Activations