© 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. 117200
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
     וגם
    -0.93
     aswell
    -0.92
    nă
    -0.92
     kokos
    -0.87
    Idk
    -0.87
     sezonu
    -0.87
     such
    -0.85
     також
    -0.85
     theyre
    -0.85
     srebr
    -0.84
    POSITIVE LOGITS
    ocities
    0.90
    あたり
    0.86
    köping
    0.82
     PLOS
    0.82
     tasked
    0.79
     Dentro
    0.79
    随之
    0.78
     endings
    0.77
     کام
    0.77
     wor
    0.76
    Activations Density 0.001%

    No Known Activations