© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76124
    Prev
    Next
    INDEX
    Explanations

    Anderson names

    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
    thora
    -0.87
     SGS
    -0.82
     adduced
    -0.80
    Ա
    -0.74
     盘
    -0.74
    യാ
    -0.74
     Apparent
    -0.73
    cuno
    -0.73
    RESOLVED
    -0.71
     نع
    -0.71
    POSITIVE LOGITS
     Anderson
    0.90
    Anderson
    0.84
     dụ
    0.82
     hopelessness
    0.81
    木製
    0.75
    otka
    0.74
     ANDERSON
    0.73
    lessly
    0.73
     insulator
    0.71
     мощность
    0.71
    Activations Density 0.011%

    No Known Activations