© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27759
    Prev
    Next
    INDEX
    Explanations

    phishing, email, spear, whaling

    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_40_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
    algèbre
    0.51
    ันทร์
    0.42
    აძ
    0.41
    莲
    0.41
    indexer
    0.40
    Astronom
    0.40
    Locator
    0.40
    legen
    0.40
    ồn
    0.39
    tbLabel
    0.39
    POSITIVE LOGITS
     phishing
    0.69
     spear
    0.64
     spoof
    0.61
    钓
    0.59
     lures
    0.57
     Emails
    0.57
     email
    0.56
     Email
    0.55
     emails
    0.55
     Spear
    0.54
    Activations Density 0.028%

    No Known Activations