© 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. 55975
    Prev
    Next
    INDEX
    Explanations

    shortening or shortening things

    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
    vejte
    -0.85
     więks
    -0.84
    жере
    -0.79
     nagyobb
    -0.79
     größeren
    -0.78
     suéter
    -0.77
     lambat
    -0.75
     diputado
    -0.75
    ⛏
    -0.71
     wyposaż
    -0.71
    POSITIVE LOGITS
     shortened
    5.78
     shorten
    5.72
     shortening
    5.59
     shorter
    5.09
     Shorter
    4.25
    short
    4.00
     short
    3.92
     Short
    3.89
    Short
    3.80
     shortest
    3.64
    Activations Density 0.168%

    No Known Activations