© 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. 220029
    Prev
    Next
    INDEX
    Explanations

    subjects are, parking is, promoted by

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

    ceo seeking advice

    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
    4
    0.55
     Los
    0.54
     Buenos
    0.52
    3
    0.48
    2
    0.46
     Dublin
    0.46
    6
    0.46
     NASA
    0.45
     Cuba
    0.44
    1
    0.44
    POSITIVE LOGITS
    bardziej
    0.52
    লগ্ন
    0.52
     उर्फ
    0.51
    prés
    0.49
    PlayerDataCache
    0.48
    ganggu
    0.48
    ভাঁ
    0.48
    कह
    0.47
     ప్రశ్న
    0.47
    র্ক
    0.47
    Activations Density 0.000%

    No Known Activations