© 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. 4986
    Prev
    Next
    INDEX
    Explanations

    specific named entities and their context

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

    act Initiatives, ott School, ble AI, ive Lung

    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
    \
    0.43
    <
    0.40
    i
    0.36
     ICM
    0.36
    Υ
    0.36
    Ν
    0.36
     ic
    0.36
     komple
    0.36
    佘
    0.36
     szkol
    0.35
    POSITIVE LOGITS
    ฯ
    0.52
     jejich
    0.43
     அவர்களின்
    0.43
     उनकी
    0.42
     তাদের
    0.41
     તેમની
    0.41
    他們的
    0.40
     jų
    0.40
    ವರಿಗೆ
    0.40
    겠지만
    0.39
    Activations Density 0.286%

    No Known Activations