© 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. 98331
    Prev
    Next
    INDEX
    Explanations

    words starting with H

    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
    INY
    -0.77
    写真
    -0.77
    毎年
    -0.76
    anyeol
    -0.75
     Kontakte
    -0.74
     fald
    -0.74
     Castile
    -0.74
     recientes
    -0.73
    ~$
    -0.72
    皆さん
    -0.71
    POSITIVE LOGITS
    threading
    0.85
    jarah
    0.82
    heroes
    0.76
     miejsc
    0.75
    phil
    0.75
    陷
    0.72
    Prueba
    0.72
    MediaPlayer
    0.71
     祝
    0.71
    を実施
    0.70
    Activations Density 0.006%

    No Known Activations