© 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. 66273
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
     comerci
    -1.04
    bicara
    -0.89
    albeit
    -0.86
    🤙
    -0.81
    غيل
    -0.81
    كين
    -0.80
     erkennt
    -0.78
     {}",
    -0.78
     novelas
    -0.78
     ciclo
    -0.77
    POSITIVE LOGITS
     AY
    0.85
     Xa
    0.83
     ندارم
    0.79
     ACA
    0.79
     oameni
    0.79
    REAT
    0.78
     diriger
    0.77
    голо
    0.77
     जाते
    0.77
    envoyer
    0.77
    Activations Density 0.000%

    No Known Activations