© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116144
    Prev
    Next
    INDEX
    Explanations

    identity theft and crises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ."
    -1.05
    S
    -1.02
    ことなく
    -1.02
     pointed
    -0.98
    '
    -0.97
     传统
    -0.96
     introductory
    -0.94
     อย่าง
    -0.91
    E
    -0.90
    </h3>
    -0.90
    POSITIVE LOGITS
     theft
    1.40
     Theft
    1.27
     IDENTITY
    1.16
    identity
    1.15
    theft
    1.10
     crises
    1.08
    merzen
    1.08
     Identity
    1.07
     identity
    1.05
     Magyar
    1.05
    Activations Density 0.012%

    No Known Activations