© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30035
    Prev
    Next
    INDEX
    Explanations

    about me

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

    structured romantic phrases

    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
    Negative Logits
     скажу
    0.46
    選択
    0.46
     символ
    0.46
     μας
    0.44
    brock
    0.43
     정부
    0.43
     comentario
    0.43
     사회
    0.42
    🔁
    0.42
     Canva
    0.41
    POSITIVE LOGITS
     entree
    0.49
    দ্ধ
    0.48
     nourriture
    0.47
     singularity
    0.45
     parse
    0.45
     experimental
    0.44
     Superintendent
    0.44
     superintendent
    0.44
     Combine
    0.44
     একসঙ্গে
    0.44
    Activations Density 0.000%

    No Known Activations