© 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. 84333
    Prev
    Next
    INDEX
    Explanations

    either version or later

    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
     yakin
    -1.02
     some
    -0.96
     Viena
    -0.90
     Seigneur
    -0.88
    lauben
    -0.85
    Asthma
    -0.85
    claro
    -0.82
     Partido
    -0.82
     Automó
    -0.81
     it
    -0.80
    POSITIVE LOGITS
     mystical
    1.07
    gnum
    1.02
    lase
    0.98
    stonia
    0.98
    ORS
    0.98
    ULTS
    0.98
    levance
    0.97
    ὴν
    0.97
    Subtract
    0.96
     impresionantes
    0.94
    Activations Density 0.004%

    No Known Activations