© 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. 10-GEMMASCOPE-RES-131K
    7. 944
    Prev
    Next
    INDEX
    Explanations

    booths and stalls

    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_10/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
    The
    -1.70
    1
    -1.57
    2
    -1.55
    ében
    -1.51
    seekers
    -1.46
    Going
    -1.45
     batalha
    -1.41
    moiselle
    -1.41
    értel
    -1.39
     that
    -1.38
    POSITIVE LOGITS
    ",
    1.52
     recuerdos
    1.49
     freakin
    1.48
     falsos
    1.48
     ´
    1.47
     (=
    1.46
    哢
    1.45
    
    1.45
    </strong>
    1.43
     !!!!
    1.43
    Activations Density 0.015%

    No Known Activations