© 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. 81697
    Prev
    Next
    INDEX
    Explanations

    private actual code declarations

    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
    izadas
    -0.75
     custa
    -0.74
    リューション
    -0.71
    見ても
    -0.71
     të
    -0.70
    copg
    -0.70
     כדי
    -0.69
    holland
    -0.69
    autoFocus
    -0.69
    Each
    -0.68
    POSITIVE LOGITS
     fun
    2.89
    val
    2.73
    fun
    2.72
     val
    2.67
     FUN
    1.83
     Fun
    1.64
    Fun
    1.56
    FUN
    1.47
     Val
    1.39
     companion
    1.37
    Activations Density 0.028%

    No Known Activations