© 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. 70053
    Prev
    Next
    INDEX
    Explanations

    never cross floodwaters

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

    measurement period

    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
     важных
    0.56
    après
    0.50
    ğin
    0.49
     విద్య
    0.49
    ifices
    0.49
    谆
    0.49
     bunların
    0.49
     вело
    0.48
     పిల్ల
    0.48
    Calcium
    0.48
    POSITIVE LOGITS
     I
    0.59
    Ｉ
    0.51
    点
    0.47
     index
    0.47
    指数
    0.45
    回合
    0.45
    指數
    0.44
     posting
    0.44
    閘
    0.44
    點
    0.44
    Activations Density 0.000%

    No Known Activations