© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120018
    Prev
    Next
    INDEX
    Explanations

    following [item/question/code]

    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
    𓍊
    -1.34
    埙
    -1.29
    eeeee
    -1.23
     paradigma
    -1.22
     poiché
    -1.20
    のほうが
    -1.20
    Mosa
    -1.20
    をはじめ
    -1.19
     saar
    -1.19
    nologi
    -1.16
    POSITIVE LOGITS
     There
    1.48
     there
    1.41
    ”,
    1.27
     it
    1.24
     as
    1.22
    ophthal
    1.21
     friend
    1.16
    there
    1.15
    </h2>
    1.14
    rů
    1.13
    Activations Density 0.056%

    No Known Activations