© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4985
    Prev
    Next
    INDEX
    Explanations

    scams and security threats

    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_16k_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
    SAT
    0.43
    髻
    0.43
     regression
    0.42
     locom
    0.41
     rearrangement
    0.40
    Structures
    0.40
    rotation
    0.39
     rotation
    0.39
     roots
    0.38
    Roots
    0.38
    POSITIVE LOGITS
     scammers
    1.33
     scams
    1.27
     scam
    1.21
    詐
    1.19
    骗
    1.13
     phishing
    1.12
     fraudulent
    1.10
     fraudsters
    1.09
    诈
    1.06
     frauds
    1.00
    Activations Density 0.782%

    No Known Activations