© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104090
    Prev
    Next
    INDEX
    Explanations

    vulnerability and its context

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "vulnerabilities" in technical and security contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rdoba
    -2.36
     horloge
    -2.28
    錞
    -2.22
    剮
    -2.17
     enfance
    -2.13
     aloof
    -2.09
    倅
    -2.02
     inadvert
    -1.95
     frigo
    -1.95
    alakip
    -1.94
    POSITIVE LOGITS
     
    2.55
    \
    2.48
    up
    2.31
    <em>
    2.20
    .
    2.19
    是要
    2.09
    嘚
    2.05
    8
    2.03
    1
    2.02
    3
    2.02
    Activations Density 0.005%

    No Known Activations