© 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. 50009
    Prev
    Next
    INDEX
    Explanations

    indicates requirement or necessity

    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
    Necessary
    -1.41
     NECESS
    -1.39
     Necessary
    -1.36
    necessary
    -1.13
     Necessity
    -1.06
    necess
    -1.02
     indispens
    -1.01
    essential
    -0.97
     cardin
    -0.96
     必要
    -0.93
    POSITIVE LOGITS
     required
    2.42
     require
    1.76
     requires
    1.54
     требуется
    1.42
     needed
    1.42
     требу
    1.16
    require
    1.10
     requerido
    1.09
     requerida
    1.06
     requieren
    1.05
    Activations Density 0.054%

    No Known Activations