© 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. 34-GEMMASCOPE-RES-131K
    7. 73699
    Prev
    Next
    INDEX
    Explanations

    security systems

    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
     phantom
    -0.77
     programming
    -0.77
    しようと
    -0.75
     Four
    -0.73
    考えると
    -0.72
    ignen
    -0.71
     Arquivado
    -0.71
     garments
    -0.68
    lible
    -0.68
    räger
    -0.68
    POSITIVE LOGITS
    cuz
    0.88
     accidente
    0.84
    UTA
    0.80
     FRAG
    0.80
     ridu
    0.80
    thema
    0.78
    ชั้น
    0.77
     ending
    0.77
     probabil
    0.77
     inad
    0.76
    Activations Density 0.008%

    No Known Activations