© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73343
    Prev
    Next
    INDEX
    Explanations

    assembly attributes and 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
     from
    -1.45
     when
    -1.38
     Automó
    -1.37
     all
    -1.31
     through
    -1.26
     PÅ
    -1.26
     OBITUARY
    -1.21
     Início
    -1.20
     Informações
    -1.19
     nutric
    -1.17
    POSITIVE LOGITS
    vantaged
    1.28
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.27
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.22
     Эти
    1.21
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.20
     fremden
    1.19
    Propel
    1.18
    ESPEC
    1.18
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.18
    Activations Density 0.001%

    No Known Activations