© 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. 11252
    Prev
    Next
    INDEX
    Explanations

    reporting or suggesting actions

    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
     kompeti
    -1.65
     шокола
    -1.45
    tifiable
    -1.34
     zwei
    -1.34
    􀂃
    -1.34
    痊
    -1.29
     unſ
    -1.26
    Procedimento
    -1.25
    咣
    -1.24
    ##
    
    -1.23
    POSITIVE LOGITS
     also
    1.69
    —
    1.53
     or
    1.27
     “
    1.23
     this
    1.22
     цвят
    1.22
    !
    1.20
    ”
    1.20
    dreamstime
    1.18
     even
    1.16
    Activations Density 0.070%

    No Known Activations