© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93308
    Prev
    Next
    INDEX
    Explanations

    render, return, view, redirect

    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_22/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
     who
    -1.12
     Italiano
    -0.97
     lenge
    -0.88
    vocations
    -0.87
     ▸
    -0.85
     Bạn
    -0.84
    who
    -0.84
     lorsque
    -0.83
    mientos
    -0.83
     ем
    -0.82
    POSITIVE LOGITS
     трябва
    1.09
    spedes
    1.05
     to
    1.04
     amiable
    1.04
    olesterol
    1.01
    styleUrls
    1.00
     treba
    1.00
    жешь
    0.99
    kazuje
    0.99
    ophyllum
    0.98
    Activations Density 0.000%

    No Known Activations