© 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. 65994
    Prev
    Next
    INDEX
    Explanations

    promising and suitable options

    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
    Ֆ
    -1.01
     Wikimédia
    -0.98
    通常
    -0.97
     理由
    -0.97
     alip
    -0.96
     indisponible
    -0.94
     wali
    -0.94
    arthed
    -0.94
    peka
    -0.93
     bahia
    -0.93
    POSITIVE LOGITS
     promising
    3.56
     potential
    2.39
     promise
    2.28
     suitable
    2.22
     viable
    1.95
     useful
    1.94
     promises
    1.77
     suitability
    1.70
     potentially
    1.70
     promis
    1.67
    Activations Density 0.273%

    No Known Activations