© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109264
    Prev
    Next
    INDEX
    Explanations

    private or secret information

    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
     Ks
    0.41
    щения
    0.40
    昊
    0.40
    ianSpace
    0.39
     isot
    0.39
    وش
    0.38
     ইল
    0.38
    ]_{
    0.38
     Ulster
    0.38
     Ко
    0.37
    POSITIVE LOGITS
    陽
    0.41
    阳
    0.39
    Private
    0.39
    Yang
    0.39
     nyata
    0.39
     conducive
    0.38
     privata
    0.38
     komple
    0.37
     republik
    0.37
     characteristic
    0.36
    Activations Density 0.001%

    No Known Activations