© 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. 34069
    Prev
    Next
    INDEX
    Explanations

    conflict and tensions

    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
    ἵ
    -1.21
    логические
    -1.15
     puissiez
    -1.14
     skóry
    -1.09
     muſt
    -1.08
     گیاه
    -1.07
     peixes
    -1.06
    emples
    -1.05
    Введение
    -1.05
    Descriere
    -1.04
    POSITIVE LOGITS
     retali
    1.48
     response
    1.45
     ارسال
    1.38
    頂いた
    1.27
    ַּ
    1.25
     gewöhnlich
    1.24
    וּ
    1.19
    ִּ
    1.17
     actions
    1.16
    いただいた
    1.16
    Activations Density 0.070%

    No Known Activations