© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103348
    Prev
    Next
    INDEX
    Explanations

    translation, links, German

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    طرح
    -0.84
    CHANT
    -0.78
    ˹
    -0.78
     Politica
    -0.78
    }{{
    -0.78
     Udaipur
    -0.75
    Ⱥ
    -0.74
     styrene
    -0.74
     شکل
    -0.73
    ગ
    -0.73
    POSITIVE LOGITS
    translation
    0.81
     jerky
    0.80
    }_{+
    0.76
    溺
    0.74
     dólares
    0.73
    ↵↵↵↵↵↵↵
    0.73
    ätä
    0.72
    髙
    0.72
     Erm
    0.71
    Übersetzung
    0.71
    Activations Density 0.015%

    No Known Activations