© 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. 53977
    Prev
    Next
    INDEX
    Explanations

    Rewards cards

    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
    ilor
    -0.85
    بدأ
    -0.81
    ∧
    -0.76
    brainly
    -0.75
    太
    -0.75
    Iran
    -0.72
    aug
    -0.71
    Israel
    -0.71
    вшая
    -0.71
     Kø
    -0.68
    POSITIVE LOGITS
     rebel
    0.97
     Id
    0.96
     northwest
    0.86
     hydroxide
    0.85
    Northwest
    0.84
     Northwest
    0.82
    rebel
    0.79
    verlet
    0.79
     skills
    0.79
    bao
    0.79
    Activations Density 0.020%

    No Known Activations