© 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. 10-GEMMASCOPE-RES-131K
    7. 20594
    Prev
    Next
    INDEX
    Explanations

    defeat and destroy entities

    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
     they
    -1.27
     we
    -1.26
     recounts
    -1.20
    ৄ
    -1.14
     hivyo
    -1.14
     bekom
    -1.13
     dring
    -1.09
     it
    -1.05
     gescha
    -1.05
    这么说
    -1.04
    POSITIVE LOGITS
     first
    1.32
     okol
    1.28
     cumplido
    1.27
    Зміст
    1.27
    咻
    1.23
     naissance
    1.22
     szükség
    1.21
     oprav
    1.20
    zestaw
    1.20
     ennen
    1.20
    Activations Density 0.036%

    No Known Activations