© 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. 117411
    Prev
    Next
    INDEX
    Explanations

    assignments and arithmetic operators

    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
     dáms
    -0.99
     própria
    -0.99
    がなく
    -0.98
     никто
    -0.97
     crucero
    -0.96
     dámské
    -0.95
     páns
    -0.92
     utilisent
    -0.92
    rahat
    -0.92
    phim
    -0.92
    POSITIVE LOGITS
     +=
    1.22
     increasingly
    1.00
     cada
    0.98
     also
    0.97
    ++;
    0.94
     indiv
    0.94
    append
    0.94
    appendChild
    0.88
    Builder
    0.88
     like
    0.87
    Activations Density 0.009%

    No Known Activations