© 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. 30917
    Prev
    Next
    INDEX
    Explanations

    data type declarations

    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
    phonse
    -0.78
     between
    -0.78
    ukov
    -0.77
    ssohn
    -0.76
    Caso
    -0.74
    olov
    -0.73
     strategies
    -0.72
     credi
    -0.71
     pourra
    -0.71
     sizes
    -0.69
    POSITIVE LOGITS
     Object
    1.09
    Object
    1.00
     double
    0.84
     való
    0.83
     объек
    0.82
    χαν
    0.82
     Double
    0.81
     OBJECT
    0.81
     Newtonian
    0.79
    Double
    0.76
    Activations Density 0.004%

    No Known Activations