© 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. 112530
    Prev
    Next
    INDEX
    Explanations

    asking about things

    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
    ↵↵
    -1.18
    ൎ
    -1.13
     parroquia
    -1.13
    ialmente
    -1.12
     messo
    -1.11
    GRAFIA
    -1.10
     dapat
    -1.10
    celotti
    -1.08
     berhasil
    -1.07
    gangenen
    -1.06
    POSITIVE LOGITS
     empê
    1.70
     their
    1.40
     ويت
    1.36
     करती
    1.34
     Either
    1.30
     élar
    1.30
     aceea
    1.23
     about
    1.23
     betreff
    1.21
     décé
    1.21
    Activations Density 0.082%

    No Known Activations