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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57098
    Prev
    Next
    INDEX
    Explanations

    Marvel titles, team context

    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
     CES
    -0.94
     آنچه
    -0.86
    зем
    -0.85
    Obfuscated
    -0.82
    ariste
    -0.80
    ances
    -0.80
    āb
    -0.80
    cheduled
    -0.79
    phors
    -0.79
     COOL
    -0.79
    POSITIVE LOGITS
     team
    1.34
     could
    1.05
     either
    0.96
     dator
    0.96
    team
    0.93
    团队
    0.93
     morals
    0.91
    Team
    0.89
    Due
    0.86
     majority
    0.84
    Activations Density 0.005%

    No Known Activations