© 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. 219500
    Prev
    Next
    INDEX
    Explanations

    work, volunteer, HR, blog, attendance

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

    develop, discover, achieve

    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
     =
    0.53
     sub
    0.47
     legisl
    0.46
     humanos
    0.45
    am
    0.44
     banked
    0.43
     meson
    0.43
     dozens
    0.41
     pump
    0.41
     trabalhadores
    0.41
    POSITIVE LOGITS
    觉得
    0.55
    发现
    0.54
    发展
    0.50
    ེ
    0.49
    𝚍
    0.49
    殒
    0.49
    爱好
    0.48
    认定
    0.48
    呓
    0.48
    𝑵
    0.47
    Activations Density 0.000%

    No Known Activations