© 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. 32852
    Prev
    Next
    INDEX
    Explanations

    seeking someone or something

    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
    名
    -0.84
     рекоменду
    -0.84
     labor
    -0.82
    タ
    -0.77
    始
    -0.77
    卤
    -0.77
    print
    -0.76
    EMENT
    -0.75
    biamo
    -0.75
     resolve
    -0.73
    POSITIVE LOGITS
     اهل
    1.09
    seeking
    1.05
     looking
    1.00
     Seeking
    1.00
     educated
    0.99
    itious
    0.96
     seeking
    0.95
    Occupation
    0.94
    Seeking
    0.93
    Mature
    0.93
    Activations Density 0.047%

    No Known Activations