© 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. 237143
    Prev
    Next
    INDEX
    Explanations

    Rahul Gandhi performed aggregated know how

    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
    計画
    0.49
     หนู
    0.48
    瓮
    0.44
    伟大
    0.44
    娠
    0.43
     характери
    0.43
    位数
    0.42
    验收
    0.42
    戕
    0.42
     QUALITY
    0.41
    POSITIVE LOGITS
    claiming
    0.49
     gegen
    0.47
     quen
    0.47
     til
    0.46
     }=
    0.46
     quas
    0.46
     millioner
    0.46
     virtually
    0.45
     kiu
    0.45
    _
    0.44
    Activations Density 0.001%

    No Known Activations