© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232298
    Prev
    Next
    INDEX
    Explanations

    estate agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bowed
    0.47
    ham
    0.46
     TVs
    0.42
     televisions
    0.42
    shadow
    0.42
     സഹ
    0.41
    镣
    0.41
    orn
    0.40
     Gut
    0.40
    一座
    0.40
    POSITIVE LOGITS
     pola
    0.54
    סי
    0.46
     dinámica
    0.45
    (*(
    0.45
     dynamique
    0.44
     notre
    0.43
     risque
    0.43
     clicking
    0.43
     রোল
    0.43
     budding
    0.42
    Activations Density 0.000%

    No Known Activations