© 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. 64971
    Prev
    Next
    INDEX
    Explanations

    quoting strings in code

    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
    s
    -1.26
    These
    -1.02
     these
    -1.01
     while
    -0.95
    設施
    -0.91
    0
    -0.91
     We
    -0.91
     Obviously
    -0.90
    ～！
    -0.90
     by
    -0.88
    POSITIVE LOGITS
     interesados
    1.22
    adds
    1.20
     varones
    1.18
     komfort
    1.16
     Usar
    1.15
    
    1.10
     seleccionados
    1.08
     jednej
    1.07
    ából
    1.05
     betaling
    1.05
    Activations Density 0.016%

    No Known Activations