© 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. 15074
    Prev
    Next
    INDEX
    Explanations

    fighting against opponents

    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
    образие
    -1.24
     séjours
    -1.23
    וּ
    -1.21
    ﻹ
    -1.19
     rayures
    -1.16
     sederhana
    -1.10
    Komentar
    -1.09
    brtc
    -1.07
     chronicles
    -1.06
     coffre
    -1.06
    POSITIVE LOGITS
     his
    1.47
     fighting
    1.41
     against
    1.34
    ३
    1.23
     facing
    1.20
     UMKM
    1.16
     против
    1.13
     opponent
    1.13
     attacking
    1.13
     fight
    1.11
    Activations Density 0.011%

    No Known Activations