© 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. 112
    Prev
    Next
    INDEX
    Explanations

    sports, events, and specific entities

    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
     системой
    -1.12
    あんまり
    -1.10
    četně
    -1.10
     so
    -1.09
    ární
    -1.09
    țiuni
    -1.08
     tunik
    -1.07
    私たちの
    -1.06
     our
    -1.05
     tradiciones
    -1.04
    POSITIVE LOGITS
     will
    1.71
    imbursement
    1.45
    Ḱ
    1.33
    addContainerGap
    1.30
     весело
    1.27
     weekend
    1.19
     acest
    1.16
    laatst
    1.15
     guapa
    1.13
    
    1.13
    Activations Density 0.007%

    No Known Activations