© 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. 90505
    Prev
    Next
    INDEX
    Explanations

    fed up

    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
     third
    -0.84
    戦争
    -0.73
     jakim
    -0.70
    Bha
    -0.69
     fourth
    -0.69
     Crews
    -0.68
     sixth
    -0.68
    rão
    -0.67
     McAfee
    -0.67
    Jpa
    -0.65
    POSITIVE LOGITS
     сельского
    0.74
     lacing
    0.69
    ABET
    0.66
     שא
    0.65
     Dal
    0.65
     wel
    0.65
     Marxism
    0.64
    懸
    0.63
     Als
    0.62
    uan
    0.62
    Activations Density 0.051%

    No Known Activations