© 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. 64278
    Prev
    Next
    INDEX
    Explanations

    science fiction

    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
     Molière
    -0.85
     akade
    -0.84
     magnetization
    -0.84
     vokal
    -0.82
     marmor
    -0.82
    Mustang
    -0.82
     Matisse
    -0.82
     Bismarck
    -0.82
     binatang
    -0.81
    órc
    -0.81
    POSITIVE LOGITS
     futuristic
    3.06
     sci
    3.05
     science
    2.83
     Sci
    2.45
    sci
    2.39
    Sci
    2.22
     Science
    2.20
    fut
    2.19
     futu
    2.17
     ciencia
    2.09
    Activations Density 0.135%

    No Known Activations