© 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. 81148
    Prev
    Next
    INDEX
    Explanations

    un-, in-, ir- prefixes

    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
    Слайд
    -0.82
     relevant
    -0.82
     substantial
    -0.79
     зре
    -0.77
     linge
    -0.77
    લા
    -0.75
    relevant
    -0.75
    consistent
    -0.74
    عتقد
    -0.72
    distinct
    -0.72
    POSITIVE LOGITS
    replaceable
    1.10
     replaceable
    1.07
     equiv
    0.99
    miss
    0.98
    contain
    0.92
    Replace
    0.91
     ordinary
    0.91
     Replace
    0.88
    replace
    0.86
    REPLACE
    0.86
    Activations Density 0.039%

    No Known Activations