© 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. 34-GEMMASCOPE-RES-131K
    7. 33504
    Prev
    Next
    INDEX
    Explanations

    quantified differences or positions

    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_34/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
     far
    -0.93
     slightly
    -0.91
     farol
    -0.82
     located
    -0.82
     далеко
    -0.82
     noticeably
    -0.75
    ﺼ
    -0.75
    lussen
    -0.75
    entamiento
    -0.75
     whose
    -0.75
    POSITIVE LOGITS
     off
    1.20
     behind
    1.19
     adrift
    1.15
     hinten
    0.96
     clear
    0.94
    clear
    0.92
     drift
    0.87
     back
    0.85
     fuera
    0.84
    ूप
    0.82
    Activations Density 0.014%

    No Known Activations