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. 10-GEMMASCOPE-RES-131K
    4. 182
    Prev
    Next
    INDEX
    Explanations

    night

    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_10/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
    饪
    -1.52
    赁
    -1.41
    cestors
    -1.38
    si
    -1.33
    actéristi
    -1.32
     tivi
    -1.31
    けれど
    -1.30
    larg
    -1.30
     bì
    -1.30
     for
    -1.28
    POSITIVE LOGITS
     there
    2.02
     it
    1.51
     religione
    1.48
    梣
    1.45
    sleep
    1.38
     procedura
    1.38
    ቷ
    1.37
     夜
    1.37
     Società
    1.35
     Overnight
    1.33
    Activations Density 0.016%

    No Known Activations