© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30415
    Prev
    Next
    INDEX
    Explanations

    Tele, Zone, Introduction

    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
    ☕
    -0.92
     continue
    -0.76
     despite
    -0.76
     even
    -0.76
    باد
    -0.75
     painel
    -0.75
     simak
    -0.74
     lusso
    -0.73
     Véri
    -0.73
     asig
    -0.72
    POSITIVE LOGITS
    だい
    0.91
     رفته
    0.89
     Krzysztof
    0.88
     життя
    0.86
    üße
    0.84
     německ
    0.84
    らない
    0.83
     aldrig
    0.83
    Limitations
    0.82
     pw
    0.82
    Activations Density 0.003%

    No Known Activations