© 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. 77785
    Prev
    Next
    INDEX
    Explanations

    Islamic Republic, Resistance, Shia, State, Military, tradition, thought, prophet

    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
     Giugno
    -0.77
    ऍ
    -0.76
     リビング
    -0.76
     BIS
    -0.75
     verkaufen
    -0.75
     родителей
    -0.75
     barbershop
    -0.75
     Kese
    -0.75
    These
    -0.75
    只是
    -0.75
    POSITIVE LOGITS
    ESSIONS
    0.93
     Defenders
    0.91
    izace
    0.90
    罡
    0.90
     adhesive
    0.89
     linie
    0.86
     Republic
    0.86
     Swim
    0.84
     artikkeli
    0.84
     Azad
    0.83
    Activations Density 0.011%

    No Known Activations