© 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. 118500
    Prev
    Next
    INDEX
    Explanations

    Mass Effect, Bioshock, options

    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
     Philo
    -0.84
     OZ
    -0.80
     Meteoro
    -0.78
     lumina
    -0.77
    LTRB
    -0.75
    ниците
    -0.75
     meteoro
    -0.73
     GBA
    -0.71
     Climat
    -0.71
    릿
    -0.71
    POSITIVE LOGITS
     Mass
    1.32
     biotic
    1.32
     Shepard
    1.28
    biotic
    1.27
    biotics
    1.23
     Citadel
    1.17
    Mass
    1.13
     Normandy
    1.09
    Miranda
    1.01
    loyalty
    0.94
    Activations Density 0.015%

    No Known Activations