© 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. 34-GEMMASCOPE-RES-131K
    7. 93096
    Prev
    Next
    INDEX
    Explanations

    everyone is / wants / knows

    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_34/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
     également
    -1.31
     ewigen
    -1.23
    另外
    -1.23
     renowned
    -1.22
    它们
    -1.21
    了很多
    -1.20
     vielen
    -1.19
     molti
    -1.17
     değiştir
    -1.16
     diğer
    -1.14
    POSITIVE LOGITS
     else
    3.23
     who
    2.59
     including
    1.70
     in
    1.66
    Else
    1.64
     Including
    1.61
    else
    1.55
    ELSE
    1.39
     involved
    1.38
     except
    1.35
    Activations Density 0.025%

    No Known Activations