© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    emerging patterns and trends

    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
     Trabajo
    -0.92
     museos
    -0.91
    lijst
    -0.88
    Ҝ
    -0.87
     cartões
    -0.87
    fassen
    -0.87
    included
    -0.86
    INLINE
    -0.85
    措施
    -0.85
    Nex
    -0.85
    POSITIVE LOGITS
     established
    1.65
     emerging
    1.55
     emerge
    1.53
     emerges
    1.37
     establish
    1.34
     emerged
    1.30
     whereby
    1.30
     patterns
    1.30
     establishes
    1.26
     Established
    1.26
    Activations Density 0.040%

    No Known Activations