© 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. 34-GEMMASCOPE-RES-131K
    4. 109322
    Prev
    Next
    INDEX
    Explanations

    zoom

    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
     trase
    -0.91
     descrizione
    -0.90
     ottima
    -0.83
    astar
    -0.82
    ”:
    -0.82
     depois
    -0.82
    $$
    
    -0.81
    ﻃ
    -0.80
     હ
    -0.80
     métodos
    -0.80
    POSITIVE LOGITS
    out
    1.13
    Into
    0.95
     Rooms
    0.93
     快乐
    0.90
     out
    0.90
     zoom
    0.86
    OUT
    0.85
     meetings
    0.85
     Zoom
    0.84
    Ideal
    0.84
    Activations Density 0.003%

    No Known Activations