© 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. 10-GEMMASCOPE-RES-131K
    7. 101776
    Prev
    Next
    INDEX
    Explanations

    statements made or released

    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
     "-
    -1.99
     第
    -1.91
    tischen
    -1.90
    AN
    -1.84
     قبل
    -1.83
    手指
    -1.81
     be
    -1.77
    ፳
    -1.77
    也能
    -1.73
    ㉗
    -1.73
    POSITIVE LOGITS
     that
    2.42
    “
    2.41
    ܜ
    2.23
    涠
    2.17
    肏
    2.16
    岨
    2.08
     STATEMENT
    2.08
    
    2.06
    tamaris
    2.03
    そういえば
    2.02
    Activations Density 0.026%

    No Known Activations