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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71712
    Prev
    Next
    INDEX
    Explanations

    Riley, Miley, Hayden

    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
    T
    -3.17
    紲
    -2.70
    ⟞
    -2.67
    遄
    -2.66
    蹚
    -2.66
     utilizzata
    -2.63
     شیپور
    -2.59
     sprawling
    -2.55
    趿
    -2.55
    ଞ
    -2.52
    POSITIVE LOGITS
     для
    2.52
    titial
    2.45
    اء
    2.38
    珖
    2.36
    "
    2.31
     For
    2.28
    釭
    2.27
          
    2.23
    s
    2.20
       
    2.17
    Activations Density 0.003%

    No Known Activations