© 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. 71515
    Prev
    Next
    INDEX
    Explanations

    Italian Mid-Century design

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

    progression after, based on

    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
    equilib
    0.52
    ū
    0.48
    ías
    0.47
    )^{-\
    0.45
    ṣ
    0.45
    quot
    0.44
    れば
    0.44
     основные
    0.43
     повністю
    0.43
     جاری
    0.43
    POSITIVE LOGITS
     इवन
    0.47
     ，
    0.46
     IT
    0.45
     中
    0.45
    后
    0.44
    扦
    0.43
    টল
    0.43
     दीजिएगा
    0.42
     技术
    0.42
     None
    0.41
    Activations Density 0.001%

    No Known Activations