© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33541
    Prev
    Next
    INDEX
    Explanations

    AutoresizingMask .assembly .permission android

    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
     hígado
    -0.91
    ifier
    -0.71
    coso
    -0.69
    LLOW
    -0.69
     rè
    -0.68
     Theorem
    -0.68
     ELL
    -0.68
    textures
    -0.67
     Sampson
    -0.67
     Daw
    -0.67
    POSITIVE LOGITS
     Nutr
    0.66
    магази
    0.65
    umpul
    0.63
    \}\\
    0.63
    topRight
    0.62
    Smith
    0.60
    bora
    0.60
    ٕ
    0.60
     betrachten
    0.60
    えば
    0.59
    Activations Density 0.054%

    No Known Activations