© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129735
    Prev
    Next
    INDEX
    Explanations

    number or code

    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_22/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
     benessere
    -0.96
     special
    -0.95
     personaggio
    -0.92
    跑去
    -0.91
     compito
    -0.90
    about
    -0.88
    ¿
    -0.82
     ABOUT
    -0.81
    mit
    -0.81
     possible
    -0.81
    POSITIVE LOGITS
     and
    1.38
     or
    1.00
     oğ
    0.97
     princí
    0.96
    與
    0.94
    และ
    0.93
    مقال
    0.90
    zionare
    0.88
     $\&$
    0.85
     \&
    0.85
    Activations Density 0.012%

    No Known Activations