© 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. 56119
    Prev
    Next
    INDEX
    Explanations

    place or location names

    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
     our
    -1.07
     estrateg
    -1.05
     every
    -1.04
     kemarin
    -0.95
     have
    -0.94
    essandro
    -0.92
    ئین
    -0.91
    ૉ
    -0.88
     each
    -0.86
    litude
    -0.86
    POSITIVE LOGITS
     gewünschten
    1.30
     zubere
    1.05
     hesit
    1.05
     passenden
    1.03
     leistungs
    1.00
    igte
    0.99
     tohto
    0.99
     OTO
    0.96
     liksom
    0.96
     vorsichtig
    0.96
    Activations Density 0.026%

    No Known Activations