© 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. 99088
    Prev
    Next
    INDEX
    Explanations

    JSON filtering parameters

    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
    es
    -2.25
    ╍
    -2.16
     illustratie
    -2.09
    <bos>
    -2.05
     rique
    -2.05
     \
    -2.02
     mulig
    -2.00
    _{
    -1.99
     kym
    -1.99
    鰱
    -1.98
    POSITIVE LOGITS
     are
    3.20
    ISHMENT
    2.34
     Änderungen
    2.34
     také
    2.33
     WHILE
    2.23
    ↵↵
    2.23
    栳
    2.13
     podem
    2.11
    真的是
    2.11
    lgari
    2.09
    Activations Density 0.002%

    No Known Activations