© 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. 47845
    Prev
    Next
    INDEX
    Explanations

    forced actions and conditions

    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
     procedentes
    -1.36
    が良い
    -1.34
    {
    -1.32
    なもの
    -1.31
    感じです
    -1.22
     friv
    -1.22
     inga
    -1.21
     (
    -1.21
    亵
    -1.20
    esis
    -1.20
    POSITIVE LOGITS
     for
    2.13
     by
    1.85
     have
    1.45
     a
    1.43
     through
    1.39
     memilih
    1.38
     on
    1.37
    ländischen
    1.35
    เพื่อ
    1.35
     become
    1.34
    Activations Density 0.069%

    No Known Activations