© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26190
    Prev
    Next
    INDEX
    Explanations

    remedy and removal

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

    components and descriptions

    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
    ly
    0.48
     autocratic
    0.47
    піль
    0.45
     гражда
    0.44
    ocratic
    0.44
     аўтаматы
    0.44
    に加え
    0.44
    晟
    0.43
     сприя
    0.42
     несмотря
    0.42
    POSITIVE LOGITS
    去掉
    0.51
     wildflower
    0.48
     watercolors
    0.47
     wildflowers
    0.46
    皤
    0.45
     superheroes
    0.44
    宠
    0.44
     রোগের
    0.44
     删除
    0.43
     mermaid
    0.43
    Activations Density 0.000%

    No Known Activations