© 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. 67212
    Prev
    Next
    INDEX
    Explanations

    code comments and annotations

    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
     anún
    -1.19
    🩻
    -1.09
    Также
    -1.05
    Intellectual
    -1.05
     saveurs
    -1.05
    ):-
    -1.05
     书法
    -1.04
     herido
    -1.04
     şun
    -1.04
     iniziare
    -1.02
    POSITIVE LOGITS
     this
    1.41
     %
    1.09
     here
    1.06
    為に
    1.03
     can
    0.97
     to
    0.96
    ,'
    0.96
    竟
    0.95
     changed
    0.95
     I
    0.94
    Activations Density 0.024%

    No Known Activations