© 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. 32977
    Prev
    Next
    INDEX
    Explanations

    Lindsey Graham

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

    Former roles, Nullification

    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
     librarian
    0.46
    疗
    0.44
    误差
    0.44
    헿
    0.43
     বিষয়
    0.43
     wyra
    0.43
     对于
    0.42
     স্নাত
    0.42
    三种
    0.42
     Tonic
    0.42
    POSITIVE LOGITS
    do
    0.55
    う
    0.52
    ウ
    0.51
    rad
    0.50
     ajud
    0.49
    ように
    0.49
    ag
    0.48
    ob
    0.48
    私たちは
    0.48
    stein
    0.47
    Activations Density 0.002%

    No Known Activations