© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16195
    Prev
    Next
    INDEX
    Explanations

    sayings and declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     பற்றி
    0.47
     について
    0.42
     होते
    0.42
     பற்றிய
    0.40
    etric
    0.40
     rell
    0.38
    <unused582>
    0.38
     მიმო
    0.38
    タリー
    0.38
     வெப்ப
    0.37
    POSITIVE LOGITS
     saying
    1.08
     "¿
    1.03
     slogan
    1.02
    一句
    0.97
    :“
    0.95
     motto
    0.94
     phrase
    0.91
     frase
    0.91
     “‘
    0.90
     diciendo
    0.89
    Activations Density 0.256%

    No Known Activations