© 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. 43635
    Prev
    Next
    INDEX
    Explanations

    employer reference or anomaly detection

    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_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
    ເນ
    0.52
     בצ
    0.49
    Spar
    0.46
    ដែលមាន
    0.45
     הכ
    0.44
    受信
    0.44
     bê
    0.44
    𝗘
    0.44
     הד
    0.43
     ظرف
    0.43
    POSITIVE LOGITS
     vault
    0.46
     billing
    0.45
     billet
    0.42
     how
    0.40
     detail
    0.40
     synonym
    0.40
     vaults
    0.39
     money
    0.39
    this
    0.39
     uang
    0.39
    Activations Density 0.000%

    No Known Activations