© 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. 22-GEMMASCOPE-RES-131K
    4. 36505
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases and definitions

    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
     peluche
    -1.31
     pelu
    -1.30
     bander
    -1.30
     Ministre
    -1.27
     appartiennent
    -1.26
     deviennent
    -1.25
     reager
    -1.24
     dourado
    -1.23
     kontro
    -1.22
     pijama
    -1.22
    POSITIVE LOGITS
    al
    1.57
    A
    1.51
     as
    1.49
    D
    1.48
    en
    1.45
    K
    1.44
    _
    1.42
     time
    1.39
    :
    1.38
    k
    1.38
    Activations Density 0.046%

    No Known Activations