© 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. 119082
    Prev
    Next
    INDEX
    Explanations

    return values or types

    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
    encji
    -0.89
    atrième
    -0.81
    щите
    -0.79
    pení
    -0.75
    rishnan
    -0.75
    leck
    -0.75
     Recurrent
    -0.74
     initiale
    -0.73
     Congregational
    -0.73
    тали
    -0.72
    POSITIVE LOGITS
     return
    3.80
    返回值
    3.33
     returns
    2.92
     returned
    2.92
     Return
    2.83
    ReturnValue
    2.77
    return
    2.73
    Return
    2.58
     returning
    2.55
    RETURN
    2.55
    Activations Density 0.093%

    No Known Activations