© 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. 22-GEMMASCOPE-RES-131K
    4. 70874
    Prev
    Next
    INDEX
    Explanations

    declaration or definition

    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_22/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
    CEPT
    -0.89
     actuales
    -0.89
    guang
    -0.88
     here
    -0.85
    oose
    -0.84
     huidige
    -0.83
    сюда
    -0.83
    institute
    -0.81
     alcune
    -0.81
     методы
    -0.81
    POSITIVE LOGITS
     have
    0.90
     tendance
    0.85
     запе
    0.84
     will
    0.83
     unquestionably
    0.83
    cessed
    0.82
     hashCode
    0.81
    getResource
    0.78
    actos
    0.78
    fingerprint
    0.76
    Activations Density 0.009%

    No Known Activations