Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7690
    Prev
    Next
    INDEX
    Explanations

    information regarding

    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
     neuve
    -0.88
     messa
    -0.84
    点赞
    -0.77
     autori
    -0.76
     obed
    -0.76
     Rek
    -0.75
     misi
    -0.74
    远的
    -0.74
     giro
    -0.74
    rikt
    -0.73
    POSITIVE LOGITS
     возмо
    0.82
    medskip
    0.82
    miu
    0.79
     mű
    0.79
    了出来
    0.79
    !("{}",
    0.78
     ず
    0.77
     figyel
    0.77
    lizard
    0.76
    texte
    0.75
    Activations Density 0.001%

    No Known Activations