Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7745
    Prev
    Next
    INDEX
    Explanations

    video games

    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
     videos
    -0.83
     TV
    -0.81
    ideos
    -0.77
    占い
    -0.74
    Estou
    -0.69
     CNS
    -0.67
     sepenuhnya
    -0.67
     veins
    -0.67
     PBS
    -0.66
    mıştır
    -0.66
    POSITIVE LOGITS
    tape
    1.02
    gemä
    0.84
     inderdaad
    0.83
    CardView
    0.83
     conferencing
    0.82
     equator
    0.82
     Killed
    0.81
    \"\
    0.81
     game
    0.81
    tapes
    0.79
    Activations Density 0.022%

    No Known Activations