© 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. 42202
    Prev
    Next
    INDEX
    Explanations

    the reason for

    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
    ]
    -2.34
     bezieht
    -2.02
     ciertas
    -1.96
     ciertos
    -1.93
    కర్య
    -1.90
    ፱
    -1.89
     behaupten
    -1.89
     messed
    -1.88
     gelingt
    -1.84
    ogada
    -1.83
    POSITIVE LOGITS
     which
    2.17
     and
    2.05
     in
    1.84
     eisen
    1.77
     reizen
    1.77
     ſo
    1.70
     kleid
    1.66
     verminder
    1.63
     beslu
    1.60
     dichter
    1.59
    Activations Density 0.013%

    No Known Activations