© 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. 40752
    Prev
    Next
    INDEX
    Explanations

    q: and free riding

    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
     außergewöhn
    -1.36
     vielfäl
    -1.35
     použití
    -1.34
     autoestima
    -1.33
    夘
    -1.28
     bislang
    -1.26
     those
    -1.25
    Ꮉ
    -1.24
    あっという
    -1.23
    ヤバ
    -1.23
    POSITIVE LOGITS
    倣
    1.27
    čný
    1.20
    Ť
    1.11
    nossa
    1.09
    erapa
    1.08
    opponent
    1.05
     tekrar
    1.05
    どうも
    1.04
     —
    1.02
     лише
    1.02
    Activations Density 0.000%

    No Known Activations