© 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. 117983
    Prev
    Next
    INDEX
    Explanations

    programming syntax or foreign words

    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
    Before
    -0.94
     Before
    -0.93
     О
    -0.89
    StringCopy
    -0.85
     prí
    -0.84
     LB
    -0.82
     Pří
    -0.81
    ;
    -0.79
    UserDetails
    -0.79
     before
    -0.79
    POSITIVE LOGITS
     suscripción
    0.96
    áneas
    0.85
     PLAINT
    0.85
    eken
    0.84
     antigos
    0.82
    atting
    0.82
     オーバー
    0.81
     fiecare
    0.79
    هدف
    0.79
     PROFESSIONAL
    0.78
    Activations Density 0.000%

    No Known Activations