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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80908
    Prev
    Next
    INDEX
    Explanations

    validating code and specific topics

    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
    znacz
    -0.81
    Nikola
    -0.81
     verbe
    -0.79
     sinon
    -0.79
    ጆ
    -0.78
    ап
    -0.78
     Faculté
    -0.77
     Edin
    -0.77
    reicher
    -0.75
     Tobi
    -0.75
    POSITIVE LOGITS
     validation
    0.97
     Validation
    0.94
    Validator
    0.91
    VALIDATE
    0.86
     vàng
    0.86
     Lidé
    0.84
     présentent
    0.82
     también
    0.82
     validating
    0.81
     rule
    0.81
    Activations Density 0.004%

    No Known Activations