© 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. 136830
    Prev
    Next
    INDEX
    Explanations

    letters or satire

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

    impacts on student, mood, insulin

    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
     aliqu
    0.48
    ាស
    0.47
    কে
    0.44
    ceti
    0.44
    尔
    0.44
    衚
    0.44
    кал
    0.44
    釹
    0.44
    кә
    0.42
    그
    0.42
    POSITIVE LOGITS
     foncé
    0.49
     motivate
    0.49
     confront
    0.47
     unite
    0.46
     vividly
    0.45
     مقابلہ
    0.45
     monumental
    0.45
     lube
    0.44
     constantemente
    0.44
     outperform
    0.43
    Activations Density 0.001%

    No Known Activations