© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54497
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

    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
     blusa
    -1.30
     only
    -1.28
     like
    -1.16
    ！(
    -1.14
     or
    -1.14
     both
    -1.09
    ！（
    -1.09
    LEBR
    -1.09
     all
    -1.05
    gunakan
    -1.04
    POSITIVE LOGITS
     angefü
    1.09
    にん
    1.08
    UT
    1.08
     możesz
    1.07
     erwor
    1.04
     deoarece
    1.04
    AG
    1.03
    ult
    1.03
    Sì
    1.02
    ţele
    1.02
    Activations Density 0.000%

    No Known Activations