© 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. 22-GEMMASCOPE-RES-131K
    7. 72242
    Prev
    Next
    INDEX
    Explanations

    if and block characters

    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_22/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
    揆
    -0.98
     even
    -0.98
     soundness
    -0.90
     detergente
    -0.85
    andering
    -0.84
    GRAFÍA
    -0.83
     people
    -0.82
    springframework
    -0.82
    preneurs
    -0.82
     bahkan
    -0.82
    POSITIVE LOGITS
     if
    1.09
    如果是
    1.07
     either
    1.05
     different
    1.02
    如果
    0.98
     différents
    0.94
    if
    0.92
    ビス
    0.91
    اگر
    0.91
     entweder
    0.90
    Activations Density 0.010%

    No Known Activations