© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109722
    Prev
    Next
    INDEX
    Explanations

    San Javier

    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
     verás
    -0.81
     aceea
    -0.80
    鹏
    -0.80
     groep
    -0.79
    那人
    -0.77
    gameOver
    -0.77
     aproximativ
    -0.76
     someplace
    -0.75
    ╵
    -0.75
     Derfor
    -0.72
    POSITIVE LOGITS
     couple
    1.23
     couples
    1.18
    couple
    1.09
    Couple
    1.02
    xy
    0.98
    telé
    0.94
     Couple
    0.93
     Lovers
    0.91
     husband
    0.91
     romantic
    0.90
    Activations Density 0.053%

    No Known Activations