© 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. 10-GEMMASCOPE-RES-131K
    7. 84844
    Prev
    Next
    INDEX
    Explanations

    sports event outcomes

    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_10/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
     avesse
    -1.05
     itself
    -1.03
    titleLabel
    -1.02
    ')));
    -0.97
     에서
    -0.93
     this
    -0.93
    }]$
    -0.93
    "])
    -0.93
     amongst
    -0.92
     concorda
    -0.92
    POSITIVE LOGITS
     lumineux
    1.05
    caba
    1.04
    ynchronous
    0.98
    CHREIB
    0.96
    SIGNED
    0.91
    waktu
    0.91
    demokrat
    0.91
     intestinal
    0.90
     procurement
    0.90
    atórios
    0.89
    Activations Density 0.004%

    No Known Activations