© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98796
    Prev
    Next
    INDEX
    Explanations

    website security and standards

    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
    kozó
    -0.79
     wonen
    -0.77
     skry
    -0.77
    xxxxxx
    -0.77
     Onde
    -0.77
     vann
    -0.76
    ATV
    -0.76
     animais
    -0.76
     spirits
    -0.75
    тили
    -0.75
    POSITIVE LOGITS
     Security
    0.86
     பா
    0.85
     security
    0.82
    Security
    0.79
     психо
    0.75
    ustomed
    0.75
    vest
    0.74
     Sacrament
    0.73
     preoccupation
    0.73
     темы
    0.72
    Activations Density 0.001%

    No Known Activations