© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    api followed by slash

    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
    ▹
    -0.88
    función
    -0.84
    Funciones
    -0.84
    vein
    -0.83
    udas
    -0.82
     Métro
    -0.82
    իտ
    -0.81
    berman
    -0.81
     שוליים
    -0.81
    theoremstyle
    -0.80
    POSITIVE LOGITS
    v
    1.26
     v
    1.02
    auth
    0.88
     מאוד
    0.82
    できるので
    0.81
    Account
    0.80
    P
    0.78
    することに
    0.78
    Air
    0.77
    report
    0.77
    Activations Density 0.005%

    No Known Activations