© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific terms

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

    later, straight, Duct, wheel, groups

    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
    byshire
    0.47
    Underwater
    0.42
    eta
    0.41
    hed
    0.40
    '
    0.40
    apad
    0.39
    ulpt
    0.39
    把他
    0.39
    年轻人
    0.38
     hydrolyzed
    0.38
    POSITIVE LOGITS
    캘
    0.52
    ুরি
    0.51
     couleur
    0.50
     zej
    0.50
     மற்றொரு
    0.50
     பிரச்
    0.49
     consecuencia
    0.48
     են
    0.48
    гора
    0.47
     Cependant
    0.47
    Activations Density 0.000%

    No Known Activations