© 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. 59948
    Prev
    Next
    INDEX
    Explanations

    double-league basis

    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
    ngh
    -0.64
    SSM
    -0.63
     pisang
    -0.63
     Verg
    -0.63
    containers
    -0.63
    epr
    -0.62
    リオ
    -0.60
    withCredentials
    -0.60
     Bors
    -0.60
     Political
    -0.59
    POSITIVE LOGITS
     寶
    0.79
    ţă
    0.71
    ónima
    0.69
    spiller
    0.69
    Matricula
    0.68
    ikawa
    0.68
     bandwidth
    0.67
     Marathi
    0.65
    祭り
    0.65
    Cyclic
    0.65
    Activations Density 0.080%

    No Known Activations