© 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. 104689
    Prev
    Next
    INDEX
    Explanations

    . You

    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
     their
    -1.25
     just
    -1.15
     all
    -1.13
    ↵↵
    -1.09
    r
    -1.07
     where
    -1.06
     sué
    -1.05
    ),
    -1.04
     while
    -1.04
     get
    -1.03
    POSITIVE LOGITS
     áng
    1.31
     também
    1.28
    锹
    1.24
     trám
    1.20
    凄く
    1.20
    どうして
    1.19
     genellikle
    1.18
     telefonu
    1.17
    割と
    1.16
     disminución
    1.14
    Activations Density 0.000%

    No Known Activations