© 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. 157421
    Prev
    Next
    INDEX
    Explanations

    political and conceptual

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

    translation and language-specific phrasing

    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
    的服务
    0.45
    覺
    0.45
    ______
    0.44
     فيه
    0.43
    гу
    0.43
     muestran
    0.40
     justru
    0.40
    ঘু
    0.40
    خير
    0.39
     ______
    0.39
    POSITIVE LOGITS
     राजनीतिक
    0.50
     колек
    0.49
    አ
    0.49
    인지
    0.48
     മൂ
    0.47
    䍩
    0.47
    檸
    0.47
    conceptual
    0.47
     сочи
    0.46
     コンパクト
    0.46
    Activations Density 0.000%

    No Known Activations