© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27256
    Prev
    Next
    INDEX
    Explanations

    official communications and legal documents

    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_22/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
     eccl
    -1.27
     kutoka
    -1.00
    homonymie
    -0.97
     satış
    -0.94
     künftig
    -0.94
     roślin
    -0.94
     ἐκ
    -0.94
     baada
    -0.94
     sledo
    -0.93
     ἐν
    -0.93
    POSITIVE LOGITS
     reply
    1.67
     response
    1.37
    返信
    1.34
     replied
    1.33
     submitted
    1.27
    וּ
    1.26
    ַּ
    1.24
    ַל
    1.24
    Reply
    1.23
     RESPONSE
    1.23
    Activations Density 0.036%

    No Known Activations