© 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. 92172
    Prev
    Next
    INDEX
    Explanations

    programming keywords and links

    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
     caña
    -0.79
    asih
    -0.79
     lü
    -0.77
    enchymal
    -0.77
    appen
    -0.75
     voz
    -0.74
     Ее
    -0.74
    ereal
    -0.73
    出声
    -0.73
    镌
    -0.72
    POSITIVE LOGITS
     constituyen
    0.81
    靂
    0.80
    public
    0.79
    private
    0.79
    /**
    0.78
     キャンプ
    0.78
     private
    0.77
     public
    0.74
    都是
    0.74
     permanently
    0.73
    Activations Density 0.001%

    No Known Activations