© 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. 25933
    Prev
    Next
    INDEX
    Explanations

    using statement

    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
     to
    -1.98
     viele
    -1.48
     if
    -1.47
     obrázok
    -1.30
     všetky
    -1.29
     voren
    -1.24
    はなく
    -1.24
    <bos>
    -1.21
     obyvateľov
    -1.19
     многие
    -1.16
    POSITIVE LOGITS
    Ꮻ
    1.46
    中略
    1.35
     raport
    1.33
     tibi
    1.30
    甍
    1.29
    ܚ
    1.28
    ógicos
    1.27
    ssymb
    1.27
     appétit
    1.27
     fata
    1.26
    Activations Density 0.001%

    No Known Activations