© 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. 67773
    Prev
    Next
    INDEX
    Explanations

    code structures and abbreviations

    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
     to
    -1.39
    pensione
    -1.09
     its
    -1.06
    都不知道
    -1.05
     många
    -1.05
     العديد
    -1.05
    ^(@
    -1.00
    álny
    -0.98
     offensichtlich
    -0.96
     hlav
    -0.95
    POSITIVE LOGITS
     mainly
    1.16
    quilo
    1.13
     with
    1.10
     uds
    1.09
     jaunes
    1.09
     Marque
    1.04
    brania
    1.03
     vertes
    1.00
     marins
    0.98
     хоче
    0.97
    Activations Density 0.000%

    No Known Activations