© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77325
    Prev
    Next
    INDEX
    Explanations

    recent arrivals or long-term survivors

    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
    同学们
    -0.88
     amante
    -0.84
    格式
    -0.80
     intermedi
    -0.79
     annon
    -0.77
     astronomers
    -0.73
     Expressions
    -0.73
     Serbs
    -0.73
     Genève
    -0.71
    Students
    -0.71
    POSITIVE LOGITS
     arrivals
    1.48
     entrants
    1.43
     recruits
    1.39
     converts
    1.23
     recent
    1.15
     applicants
    1.13
     induc
    1.05
     successful
    1.02
     applicant
    1.01
     entrant
    1.01
    Activations Density 0.169%

    No Known Activations