© 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. 10-GEMMASCOPE-RES-131K
    7. 44899
    Prev
    Next
    INDEX
    Explanations

    requesting or asking questions

    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
    鈊
    -1.34
    AKU
    -1.32
    ＂
    -1.27
     этого
    -1.25
     definiti
    -1.24
     Bibliote
    -1.23
     dix
    -1.22
    uelles
    -1.21
     ciber
    -1.20
    今回は
    -1.19
    POSITIVE LOGITS
     seen
    1.50
     about
    1.45
     for
    1.38
     pomocou
    1.37
     difficoltà
    1.35
    abinieri
    1.34
     zákaz
    1.29
    ecé
    1.26
     nedost
    1.26
     všetky
    1.26
    Activations Density 0.040%

    No Known Activations