© 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. 32078
    Prev
    Next
    INDEX
    Explanations

    venia, tall, bruised, Indianapolis

    np_acts-logits-general · gemini-2.5-flash-lite

    liability, innovation, Azure, Damage

    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
     ถาม
    0.50
    Missense
    0.48
    s
    0.47
    nY
    0.47
     prostagland
    0.46
     Konto
    0.46
    dS
    0.45
    puh
    0.45
    
    0.45
    FindFileData
    0.45
    POSITIVE LOGITS
    illustration
    0.48
     février
    0.42
     समर्पण
    0.42
    ums
    0.42
     Michigan
    0.41
     shipwreck
    0.40
     Venice
    0.40
     शेअर
    0.40
    ína
    0.39
     duc
    0.39
    Activations Density 0.000%

    No Known Activations