© 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. 22-GEMMASCOPE-RES-131K
    7. 54378
    Prev
    Next
    INDEX
    Explanations

    and [verb]

    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
     VEHICLE
    -1.38
     diğer
    -1.29
    ôs
    -1.22
    其他
    -1.21
     художник
    -1.20
    отя
    -1.20
     from
    -1.18
     ló
    -1.18
     ↓,
    -1.17
     tragé
    -1.17
    POSITIVE LOGITS
     empfangen
    1.16
     will
    1.16
    為に
    0.96
     gefangen
    0.96
     разных
    0.96
    ようになりました
    0.94
    ものです
    0.93
    política
    0.92
    楽しめます
    0.92
    行きたい
    0.92
    Activations Density 0.019%

    No Known Activations