© 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. 10-GEMMASCOPE-RES-131K
    7. 59577
    Prev
    Next
    INDEX
    Explanations

    Iranian people and related contexts

    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_10/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
    )
    -1.16
    Also
    -1.12
    NSNotification
    -1.09
     للف
    -1.08
    These
    -1.06
    ことから
    -1.05
     liksom
    -1.05
    とは
    -1.05
     Also
    -1.03
    :
    -1.02
    POSITIVE LOGITS
     that
    1.31
    直至
    1.14
    Iranian
    1.10
     it
    1.05
    ליה
    1.04
     configura
    1.04
     levante
    0.98
    зовый
    0.97
     Dentro
    0.97
    名叫
    0.96
    Activations Density 0.116%

    No Known Activations