© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31071
    Prev
    Next
    INDEX
    Explanations

    linearly separable, xor operation

    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
     paramedics
    -0.85
    ůž
    -0.80
    Ꮶ
    -0.76
    Cue
    -0.76
    🥐
    -0.74
    痠
    -0.73
    Sous
    -0.72
    allel
    -0.72
    timbangan
    -0.72
     chante
    -0.71
    POSITIVE LOGITS
     decision
    1.32
    Decision
    1.27
     Decision
    1.26
    decision
    1.09
     separation
    1.06
     DECISION
    1.06
     Entscheidung
    1.03
    XOR
    0.97
     XOR
    0.96
     Separation
    0.94
    Activations Density 0.017%

    No Known Activations