© 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. 53-GEMMASCOPE-2-RES-262K
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    scam and fraud

    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_53_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
    க்கிழ
    0.46
    梏
    0.46
     conditionally
    0.44
     শক্তি
    0.42
    Attenuation
    0.41
    焖
    0.41
     attenuation
    0.40
    าที
    0.39
     restrict
    0.39
     Constraints
    0.38
    POSITIVE LOGITS
     scam
    2.84
     scams
    2.83
     fraud
    2.75
     scammers
    2.58
    Fraud
    2.58
    詐
    2.56
     fraudulent
    2.55
    fraud
    2.52
     Fraud
    2.47
     frauds
    2.42
    Activations Density 0.124%

    No Known Activations