© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67689
    Prev
    Next
    INDEX
    Explanations

    words ending in IC, LL, ENTS, RI, ULATIONS, IDENCE, s, IFFS, IVITY, ATED, ICS, IND

    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
     if
    -1.70
     of
    -1.60
     as
    -1.42
     Some
    -1.30
     What
    -1.30
     on
    -1.29
     in
    -1.27
     ungefär
    -1.27
    There
    -1.23
     like
    -1.22
    POSITIVE LOGITS
    ꯳
    1.50
     westfalen
    1.48
     semelh
    1.44
    艄
    1.43
    饜
    1.38
    棡
    1.34
    
    1.34
     geladeira
    1.34
     inizia
    1.30
    𓆏
    1.30
    Activations Density 0.126%

    No Known Activations