© 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. 228214
    Prev
    Next
    INDEX
    Explanations

    Milne says, becoming tangled

    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
     reunions
    0.53
     pipelines
    0.49
     futuras
    0.48
     premiums
    0.47
     Italians
    0.47
    朳
    0.46
    岁的
    0.46
     meinen
    0.46
    விக்கும்
    0.45
     berichten
    0.45
    POSITIVE LOGITS
     പാറ
    0.56
    astă
    0.52
     주요
    0.50
    َّة
    0.49
    नवीन
    0.49
     '}
    0.48
     코드
    0.48
    ੍ਹਾਂ
    0.48
     omoguć
    0.48
     보이는
    0.48
    Activations Density 0.000%

    No Known Activations