© 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. 58854
    Prev
    Next
    INDEX
    Explanations

    Filipino children / under political parties

    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
    éf
    -0.91
    tigas
    -0.81
     spoilt
    -0.81
    iete
    -0.81
    イエ
    -0.80
    elections
    -0.79
     Scandinavia
    -0.79
    篠
    -0.78
     premed
    -0.78
    Retries
    -0.78
    POSITIVE LOGITS
     responsive
    0.87
     pursuant
    0.82
    lementation
    0.76
     dru
    0.75
     аккумулятор
    0.74
    drug
    0.74
    ྒ
    0.74
     assistance
    0.73
    如此
    0.73
    alegal
    0.73
    Activations Density 0.003%

    No Known Activations