© 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. 26561
    Prev
    Next
    INDEX
    Explanations

    names and judicial roles

    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
    にあります
    -1.18
     magasins
    -1.14
     allerlei
    -1.13
    耵
    -1.12
     côtés
    -1.07
     jn
    -1.07
    Scopri
    -1.05
    Yamaha
    -1.05
     panneaux
    -1.04
     SOMETHING
    -1.03
    POSITIVE LOGITS
     by
    1.79
     including
    1.32
     Michael
    1.28
     Christopher
    1.24
     mostly
    1.23
     greatly
    1.21
     possibly
    1.21
     deeply
    1.20
     Peter
    1.20
     entirely
    1.20
    Activations Density 0.023%

    No Known Activations