© 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. 64781
    Prev
    Next
    INDEX
    Explanations

    .txt file paths

    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
    경
    -0.82
     Sv
    -0.80
    izin
    -0.80
    ikus
    -0.80
     燕
    -0.76
     kola
    -0.74
     Failures
    -0.74
     encephalitis
    -0.73
    Stars
    -0.72
     failures
    -0.72
    POSITIVE LOGITS
    pathname
    0.68
     institucional
    0.66
    Remarks
    0.66
    個性
    0.65
    CIL
    0.65
     foundation
    0.64
    资本
    0.64
     schick
    0.63
     визу
    0.63
     piacevole
    0.63
    Activations Density 0.060%

    No Known Activations