© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    positional words

    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
     and
    -1.72
    ”
    -1.13
    フレー
    -1.13
     with
    -1.12
    ,
    -1.11
     солнце
    -1.09
     or
    -1.08
     який
    -1.08
     سایر
    -1.07
    }
    -1.06
    POSITIVE LOGITS
    titial
    1.45
    omorphisms
    1.43
     особенно
    1.42
    riceps
    1.35
    athons
    1.32
    uyasha
    1.28
    Dentro
    1.27
    🄼
    1.27
     circunstancias
    1.27
    tissimo
    1.24
    Activations Density 0.154%

    No Known Activations