© 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. 34-GEMMASCOPE-RES-131K
    7. 50046
    Prev
    Next
    INDEX
    Explanations

    belongs_to associations

    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_34/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
    댑
    -0.78
     deca
    -0.73
    Baker
    -0.72
     نزد
    -0.69
    streng
    -0.68
    huang
    -0.68
     сму
    -0.66
     Tuber
    -0.66
    ські
    -0.64
     Lop
    -0.64
    POSITIVE LOGITS
    PubKey
    0.75
    }}:
    0.75
     nothingness
    0.72
    }}/>
    0.68
    anal
    0.68
    oub
    0.68
     incorrectly
    0.66
    inetti
    0.66
    搭配
    0.66
    remont
    0.66
    Activations Density 0.027%

    No Known Activations