© 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. 22-GEMMASCOPE-RES-131K
    7. 64831
    Prev
    Next
    INDEX
    Explanations

    books and articles

    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
     other
    -1.33
     even
    -1.30
    :
    -1.16
     invito
    -1.07
    壁纸
    -1.06
    ͉
    -1.03
    。　　
    -1.03
     while
    -1.01
     consenti
    -0.97
     verwendeten
    -0.96
    POSITIVE LOGITS
     and
    2.02
     zimowe
    1.21
     октября
    1.16
    痠
    1.16
     Edition
    1.16
     августа
    1.15
    fjspx
    1.11
     июня
    1.10
    čių
    1.09
    wikkel
    1.08
    Activations Density 0.092%

    No Known Activations