© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12190
    Prev
    Next
    INDEX
    Explanations

    honestly, frankly, and personal statements

    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_10/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
     Notably
    -2.16
     Finally
    -1.96
    谖
    -1.88
     Specifically
    -1.86
    </i>
    -1.86
     Subsequently
    -1.83
    atação
    -1.77
     Lastly
    -1.77
     Bioaccumulative
    -1.76
     Clearly
    -1.75
    POSITIVE LOGITS
    '
    1.49
     VIVO
    1.47
     DESCR
    1.45
     intenso
    1.39
     スペシャル
    1.34
     geschlagen
    1.34
     GOL
    1.33
     only
    1.31
    0
    1.31
     ENERG
    1.30
    Activations Density 0.010%

    No Known Activations