© 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. 22-GEMMASCOPE-RES-131K
    7. 64946
    Prev
    Next
    INDEX
    Explanations

    don't want to

    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_22/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
    お昼
    -1.12
     داشتند
    -1.11
     not
    -1.03
    ocyclic
    -1.01
     позволит
    -0.98
    昼食
    -0.97
    Descriere
    -0.95
    おすすめの
    -0.93
    镊
    -0.92
    ,<
    -0.92
    POSITIVE LOGITS
     or
    1.41
     anymore
    1.32
     sondern
    1.06
     necessarily
    0.98
    ড
    0.96
    又は
    0.95
    jual
    0.93
     sofort
    0.91
    theguardian
    0.91
    
    0.91
    Activations Density 0.042%

    No Known Activations