© 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. 98012
    Prev
    Next
    INDEX
    Explanations

    LICENSE.txt file

    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
    appcompat
    -0.79
    ﻘ
    -0.73
    ótica
    -0.73
    镯
    -0.73
    swing
    -0.71
     Emmer
    -0.71
    鐲
    -0.69
    īgs
    -0.69
     detour
    -0.69
     nächsten
    -0.69
    POSITIVE LOGITS
    Assemble
    0.70
     accumulate
    0.70
     てき
    0.66
     accumulated
    0.65
    Oxygen
    0.65
     Oxygen
    0.64
     furnishing
    0.64
     сп
    0.63
    Origen
    0.62
    drawiam
    0.62
    Activations Density 0.047%

    No Known Activations