© 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. 50114
    Prev
    Next
    INDEX
    Explanations

    titles, questions, and topics

    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
    сиона
    -0.74
    mici
    -0.73
    チケット
    -0.72
     licking
    -0.71
    ̢
    -0.70
     依
    -0.68
    hills
    -0.67
     quería
    -0.67
    ="%
    -0.67
     könne
    -0.66
    POSITIVE LOGITS
    čnega
    0.79
     echoes
    0.78
    ロウ
    0.77
     textField
    0.77
    žni
    0.76
     anahtar
    0.76
     composé
    0.74
    @@
    0.74
    太好了
    0.72
    ſſed
    0.72
    Activations Density 0.006%

    No Known Activations