© 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. 108712
    Prev
    Next
    INDEX
    Explanations

    fair

    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
     erforder
    -0.94
    éticos
    -0.90
    Magn
    -0.88
    𝗋
    -0.87
    翻訳
    -0.87
     empfangen
    -0.86
    Ingrese
    -0.86
     meaningfully
    -0.85
     subgoal
    -0.84
    オーバー
    -0.83
    POSITIVE LOGITS
    fair
    1.23
     treatment
    1.20
     and
    1.09
     distribution
    1.04
     assessment
    1.03
     assessments
    1.02
     representation
    1.02
     criticism
    1.02
     fair
    0.98
     chance
    0.96
    Activations Density 0.008%

    No Known Activations