© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    supposedly or allegedly

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

    detecting subjective, promotional claims of superiority or strong positive endorsements (e.g., superlatives/boastful praise).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     VERY
    0.44
    ลม
    0.43
     również
    0.42
    німа
    0.42
    Next
    0.42
    에서도
    0.42
    ové
    0.41
    ០
    0.41
     ankaŭ
    0.41
     übrigens
    0.40
    POSITIVE LOGITS
     якобы
    1.02
     supposedly
    0.79
     allegedly
    0.71
     নাকি
    0.65
     údaj
    0.61
     supposed
    0.59
     বুঝি
    0.59
     purportedly
    0.57
     somehow
    0.57
     alleged
    0.55
    Activations Density 0.153%

    No Known Activations