© 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. 118255
    Prev
    Next
    INDEX
    Explanations

    particle and what follows

    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
    4
    -1.10
    7
    -1.02
    9
    -1.02
    The
    -1.00
    1
    -0.98
    5
    -0.97
    2
    -0.96
    8
    -0.93
    <<<<<<<
    -0.91
     ton
    -0.91
    POSITIVE LOGITS
    LETIN
    1.18
     hospod
    1.08
     desmotiv
    1.08
     accelerators
    1.05
    งิน
    1.05
     Ausrüstung
    1.02
    thentication
    0.99
    ㎥
    0.98
    resize
    0.97
    
    0.96
    Activations Density 0.021%

    No Known Activations