© 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. 54072
    Prev
    Next
    INDEX
    Explanations

    accession numbers

    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
    ías
    -0.76
    wnicy
    -0.76
     coton
    -0.75
     Stok
    -0.75
     cant
    -0.73
    jnych
    -0.72
    riders
    -0.72
    мене
    -0.71
     ob
    -0.71
     mits
    -0.70
    POSITIVE LOGITS
     amps
    0.88
     چیه
    0.81
     newbie
    0.80
     코드
    0.79
    Alerter
    0.79
     worksheet
    0.78
    nieuw
    0.77
     okna
    0.76
    orté
    0.76
    ▬▬▬▬
    0.76
    Activations Density 0.076%

    No Known Activations