© 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. 216602
    Prev
    Next
    INDEX
    Explanations

    schedule, donations, infrequent reunions, questions shared

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

    words about concepts and people

    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
     nós
    0.55
    ie
    0.53
    í
    0.53
     livre
    0.50
    on
    0.50
     quem
    0.49
    yn
    0.49
    mleri
    0.48
     použí
    0.48
     desde
    0.47
    POSITIVE LOGITS
    やすい
    0.49
    澹
    0.49
    வும்
    0.48
    סים
    0.48
    穰
    0.48
    力が
    0.48
    対流
    0.47
    𒌉
    0.46
    菽
    0.46
    щает
    0.46
    Activations Density 0.001%

    No Known Activations