© 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. 184830
    Prev
    Next
    INDEX
    Explanations

    prepare for

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

    ssh key pair generation

    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
    。
    0.46
    funcionario
    0.46
    robots
    0.44
    جواب
    0.44
     sys
    0.44
    تمام
    0.43
    たす
    0.43
    ても
    0.42
    十分
    0.42
    юць
    0.42
    POSITIVE LOGITS
    汇
    0.48
     змі
    0.48
     কাহিনী
    0.47
     ибо
    0.45
     εικό
    0.44
     ইতিহাস
    0.43
     рід
    0.43
     похо
    0.42
     ημέ
    0.42
     Rockford
    0.42
    Activations Density 0.000%

    No Known Activations